Dataset Viewer
Auto-converted to Parquet
conversations
listlengths
2
2
source
stringclasses
1 value
stack
stringclasses
1 value
[ { "from": "human", "value": "Given a sentence in the Thai, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.\n\n[Q]: ท่ามกลางความสับสนกับเหตุการณ์ระเบิดวันนี้ที่กรุงลอนดอน เจ้าหน้าที่ได้ประกาศให้ประชาชนหลีกเลี่ยงเข้าตัวเมืองหากเป็นไปได้ เพื่อที่หน่วยฉุกเฉินจะได้ปฏิบัติหน้าที่ได้รวดเร็วขึ้น\n[A]: 今日のロンドンの爆発をめぐる混乱の中、当局者は救急サービスが迅速に行われるように、一般人はシティを避けるように要請した。\n\n\n[Q]: สิ่งที่ผมกังวลในฐานะผู้มีสิทธิเลือกตั้งคือปัญหาทางด้านจริยธรรม\n[A]: 有権者として、私に関心があるのは道徳的な問題だ。\n\n\n[Q]: ผู้หมวด Kevin Rooney จากกรมตำรวจ San Diego กล่าวว่า \"เจ้าหน้าที่ได้ให้คนขับไปตรวจในอันดับที่สอง และเขา [คนขับ] ก็เร่งเครื่องหนีไปอย่างรวดเร็ว\"\n[A]:" }, { "from": "gpt", "value": "サンディエゴ警察のケビン・ルーニー警部補によると、「管理官が運転手に再審査について言及したところ、被疑者は突然アクセルをふかして去って行った」と言う。\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the small-talk strategy, otherwise output No. small-talk is a cooperative negotiation strategy. It is used for discussing topics apart from the negotiation, in an attempt to build a rapport with the opponent. For example, discussing how the opponent is doing during the pandemic or sharing excitement for the camping trip.\nInput: Context: \nUtterance: 'Hi there. I'm really looking forward to this camping trip! Hope we can make a deal over these extra supplies. 🙂 I was hoping to do some hiking and swimming away from my campsite, so having some extra fresh water would be really helpful to me.'\nOutput:" }, { "from": "gpt", "value": "Yes" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "This task is about translating a given English language sentence to French.\n\nExample Input: \"The museum is putting Pac-Man alongside Picasso.\" Again.\nExample Output: \"Le musée invite Pac-Man aux côtés de Picasso\". Encore.\n\nExample Input: You got it?\nExample Output: Vous l'avez deviné ?\n\nExample Input: And using a fork to pick up a piece of broccoli from a Styrofoam plate without driving the fork through the plate is going to be as difficult as brain surgery.\nExample Output:" }, { "from": "gpt", "value": "Piquer un morceau de brocoli avec une fourchette sur une assiette en polystyrène sans traverser l'assiette sera aussi difficile qu'une opération du cerveau.\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: In this task, you are given a hateful post in Bengali that expresses hate or encourages violence in a geopolitical context based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: geopolitical or non-geopolitical depending on the topic.\nInput: শালী একটা মাগী অতিবিশিষ্ট দের ছুদা দেয় ৷ \nOutput:" }, { "from": "gpt", "value": "non-geopolitical" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task, you are given a sentence from the Bible in English, and your task is to translate it into Persian.\nTeacher: Now, understand the problem? Solve this instance: And it came to pass on the day when the LORD spake unto Moses in the land of Egypt,\nStudent:" }, { "from": "gpt", "value": "و خداوند به موسی گفت: «ببین تو را برفرعون خدا ساخته‌ام، و برادرت، هارون، نبی تو خواهد بود." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be characterized by being or having the Tail or not. Being characterized usually describes entities' general characteristics such as rose is red, or subjective attributes such as thirst is uncomfortable. It can also map to descriptors that speak to the substance or value of items such as meat has the property of being stored in the freezer or bike is powered by a person's legs. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.\nQ: Head: wine<sep>Tail: served on airplanes\nA:" }, { "from": "gpt", "value": "Yes" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Translate from English to Hindi.\n\n[EX Q]: Talking is disgraceful during services.\n[EX A]: सत्संग के दौरान बात करना अपमानजनक है.\n\n[EX Q]: He hears your tale of woe and quite naturally wants to cheer you up.\n[EX A]: वह अपनी कहानियां सुनाता है और स्वाभाविक रूप से तुम्हें खुश करना चाहता है.\n\n[EX Q]: - Rope?\n[EX A]:" }, { "from": "gpt", "value": "- रस्सी?\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be given a passage consisting of set of facts. The task is to create a question of form 'Where is <person_name>?' that is answerable from exactly one of the given facts. Avoid creating questions that are unanswerable from all of the facts.\nProblem:Passage: Daniel journeyed to the kitchen. Daniel journeyed to the bedroom. Sandra moved to the garden. Sandra went back to the kitchen. Daniel travelled to the office. Sandra went back to the hallway. Daniel journeyed to the hallway. Daniel went to the bathroom.\nSolution:" }, { "from": "gpt", "value": "Where is Sandra?" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Japanese.\n\nEx Input:\nو هنگامی که شما این کار ، را انجام می ‌ دهید این واقعا آزمایش خسته کننده ‌ ای است.\n\nEx Output:\n実験参加者にとってはほんと退屈な実験ですよ\n\n\nEx Input:\nو در آخر \"\" دِرِک \"\" فکر کنم قبول کردی که می تونم با هم از نواختن لذت ببریم.\n\nEx Output:\nついにデレクは一緒に演奏する楽しさに気づいてくれました\n\n\nEx Input:\nو حتا اگر که بیشتر از این نر ‌ های \"\" به اصطلاح \"\" عقیم داشته باشیم ، اون ‌ وقت ، نوزادان پشه ‌ در مراحل مختلف رشدشون ، می ‌ میرن. البته ، به یاد داشته باشین که من این نرها رو موقتا ، \"\" عقیم \"\" می ‌ ‌ نامم.\n\nEx Output:\n" }, { "from": "gpt", "value": "そして、これをもっと多く放せば子孫がいずれ死に絶えるオスを「無精子」と呼ぶことにしましょう\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in Bulgarian, generate a new Bulgarian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\nЩе играете на шахматна степен, защото искате да тествате уменията си.\nOutput:" }, { "from": "gpt", "value": "Вие ще играете игра на шах, защото искате да тествате залога си." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, You are given a review of Amazon's food products. Your task is to divide them into two classes: negative or positive, depending on the content of the review.\n\nEx Input:\nAfter a year of this product working fine, our internet provider recommended we do a hard reset of this device to improve the connection between this router and our modem. That’s when the problems began. Netgear spent over 30 minutes on the phone with us, found the issue and then wanted $139 for further support, more than we paid for the router initially. Escalating to a supervisor he offered a lower price but no other options other than a troubleshooting article we could have found ourselves (if we had internet connection). We have lost a day of work, still don’t have internet, Netgear doesn’t care in the least.\n\nEx Output:\nnegative\n\n\nEx Input:\nThis is easy to use and comfortable. The heat doesn’t last that long and the scented smell is so terrible that I can’t even keep the eye mask on that long.\n\nEx Output:\nnegative\n\n\nEx Input:\nThis film is absolutely incredible. Hard to watch at times, but in my opinion none of the drug use, sex, or violence is gratuitous in any way--they are all used as plot devices to tell an intricate story about the love and pain experienced by the four main characters. One of the most rewarding things about the film is that it never makes itself obvious. You can watch it and enjoy it without analyzing it, but there is so much happening underneath the surface that I would encourage anyone watching to really think about the symbols and metaphors that are presented throughout the film. Everything connects in such a beautiful way. Meow.\n\nEx Output:\n" }, { "from": "gpt", "value": "positive\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Japanese.\n\n[EX Q]: אפילו מכונת הדפוס, אפילו הדפוס נחשב לכלי שיעזור להשליט הגמוניה קתולית ברחבי אירופה.\n[EX A]: 活版印刷でさえカトリック知識人の支配をヨーロッパに広めるツールとして捉えられていたのです\n\n[EX Q]: מה שאתם עומדים לראות מהר מאד זה את ג 'וליאנו פינטו בשלד מבצע את הבעיטה כמה דקות לפני שיצאנו למגרש ועשינו את הדבר האמיתי לפני הקהל כולו, והאורות שתראו רק מתארים את המבצע.\n[EX A]: これからご覧いただくのはジュリアーノ・ピントがエクソを着てピッチに向かう数分前に蹴る動作を行い観衆たちの前で実際の動作を行った様子ですこれからご覧になる光が操作をあらわしています\n\n[EX Q]: עכשיו בעולם של נשק רובוטי זול ונפוץ, גבולות יוכלו לספק מעט מאוד הגנה למבקרים של ממשלות רחוקות או ארגוני פשע חוצי-עולם.\n[EX A]:" }, { "from": "gpt", "value": "安いロボット兵器が拡散するような世界になったら遠くにいる政府反対派や国際的犯罪組織に対し国境はほとんど防衛線になりません\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task, you are given books product reviews in German language. The goal is to classify the review as \"POS\" if the overall sentiment of the review is positive or as \"NEG\" if the overall sentiment of the review is negative.\nTeacher: Now, understand the problem? Solve this instance: Nur für \"Standard-Golf-Besitzer\" . - Diese Buchreihe hat an Qualität nachgelassen. - Es werden keine Details über den Motor beschrieben, die für Motorarbeiten wichtig wären. - Besonderheiten und Unterschiede zu dem V6 werden ausgespart. - Keine Infos, keine Bilder zum 4 Motion Antrieb. - Kein Wort zum R32 (fast gleiche Technik wie V6) - Für mich waren nur wenige Anleitungen zum Innenraum interessant. - Die meisten Anleitungen sind viel zu detailliert und an vielen Stellen zu ungenau beschrieben. - Viele Anleitungen sind sehr irreführend oder sogar falsch oder einfach nicht für alle Modelle geeignet ohne das darauf hingewiesen ist. - Das Buch ist für begabte Hobbyschrauber in den allermeisten Fällen nicht ausreichend; für den Technikinteressierten total unbrauchbar, weil die Technik nicht erklärt wird; für den unversierten Möchtegernschrauber evtl. interessant aber möglicherweise auch manchmal irreführend und diese Gruppe wird sowieso eher den häufigen Rat des Buches befolgen: \"ab zur Werkstatt\".\nStudent:" }, { "from": "gpt", "value": "NEG" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you're given statements in native Tamil language. The statement can be written with the Tamil alphabet or the English alphabet. Your job is to evaluate if the statement is offensive or not. Label the post as \"Not offensive\" if the post does not contain offense or insult. Non-offensive posts do not include any form of offense or insult. Label the post as \"Offensive\" if the post contains offensive language. \n\nEx Input:\nഈ തടിയനെ വെച്ചേ ആരെങ്കിലും പടം എടുക്കോ 🤣🤣🤣🤣🤣\n\nEx Output:\nOffensive\n\n\nEx Input:\nLast 8 sec ufff injaathi ikka ingal poliyatta\n\nEx Output:\nNot offensive\n\n\nEx Input:\nചാലക്കുടിയുടെ അഭിമാനം ലിജോ ജോസ് പല്ലിശേരിയെ അനുകരിക്കാൻ ജോഷിയുംആമേൻ\n\nEx Output:\n" }, { "from": "gpt", "value": "Not offensive\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a sentence in Persian, and your task is to translate it into English.\nPart 2. Example\nجناب گرانت خیلی دلش می‌خواست روز یکشنبه بعد از آن همه خستگی روزانه بنشیند و بوقلمون را بخورد.\nAnswer: because I know how much more Dr. Grant would enjoy it on Sunday after the fatigues of the day,\nExplanation: This is a good example. The above sentence is correctly translated from Persian to English.\nPart 3. Exercise\nروی پاکت این عبارت به چشم می‌خورد:\nAnswer:" }, { "from": "gpt", "value": "directed like a sign board to" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Portugese.\nOne example is below.\nQ: Ora, lungo il percorso, George segnala che la sua tecnologia, la tecnologia della biologia sintetica, sta accelerando molto più velocemente del tasso previsto dalla Legge di Moore.\nA: Ao longo do livro, George chama a atenção de que a sua tecnologia, a tecnologia da biologia sintética, está atualmente a acelerar a uma taxa 4 vezes superior à Lei de Moore.\nRationale: The Italian sentence is correctly translated into Portugese, because the meaning is preserved.\nQ: Io sono qui oggi per parlarvi di una nuova interessante ipotesi e di alcune nuove scoperte di straordinario peso su cui ho lavorato sul rapporto tra la struttura della lingua parlata e la nostra propensione al risparmio.\nA:" }, { "from": "gpt", "value": "Hoje vou falar-vos de uma intrigante nova hipótese e de uma série de descobertas surpreendentes nas quais tenho estado a trabalhar sobre a relação entre a estrutura da língua que falam e a vossa tendência para poupar." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "The input contains a debate topic, an argument on the topic and a keypoint, separated by \"<sep>\". Your task is to answer if the keypoint matches the argument and summarizes exactly what the argument means, in the context of the given topic.\n\n[EX Q]: Topic: We should fight for the abolition of nuclear weapons<sep>Argument: We can't trust every nuclear power to denuclearize, keeping some weapons in stock keeps peace.<sep>Keypoint: Nuclear weapons is essential for protection and deterrence\n[EX A]: True\n\n[EX Q]: Topic: We should ban the use of child actors<sep>Argument: Child actors should be banned as they miss out on growing up properly in a stable family environment and get adequate education.<sep>Keypoint: Child performers are at risk of exploitation\n[EX A]: False\n\n[EX Q]: Topic: We should ban the use of child actors<sep>Argument: Children need to be in school and with their families not working<sep>Keypoint: Child performers are at risk of exploitation\n[EX A]:" }, { "from": "gpt", "value": "False\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Q: In this task, you are given a sentence in Persian, and your task is to translate it into English.\nفلورنتینو آریثا همچنان به دیدار او می‌رفت،\nA:" }, { "from": "gpt", "value": "Florentino Ariza continued to visit her in the looted house," } ]
Flan: Non English
chosen
[ { "from": "human", "value": "This task is to translate the Telugu Language Input to English Language Output\n\nLet me give you an example: నేను వీడియో చేస్తున్నాను\nThe answer to this example can be: I am making a video.\nHere is why: Both the sentences says the same meaning in different languages, so it is a correct translation.\n\nOK. solve this:\nAria డైనింగ్ టేబుల్, డైనింగ్, Aria భోజనాల కుర్చీ, భోజనాల కుర్చీ, లింగ్ స్క్వేర్ డైనింగ్ టేబుల్, డైనింగ్ టేబుల్,\nAnswer:" }, { "from": "gpt", "value": "Aria Dining Chair, Dining Chair, Aria Dining Table, Dining Table, Ling Square Dining Table, Dining," } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you will be presented with a question having multiple possible answers in Arabic language. And you should choose a most suitable option out of \"A\", \"B\", \"C\", \"D\", and \"E\" based on your commonsense knowledge.\n\nQuestion: كانت كومة الأطباق المتسخة عالية جدًا ، فقد حان الوقت بالتأكيد إلى ماذا؟ \n Options: A رياضي B أرض C مشرق D نظيف E السرير \nOutput:" }, { "from": "gpt", "value": "D" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Generate an explanation for the given claim using the provided supporting material from the paragraph. Please consider the following points while generating an output. 1) The claim will always have supporting proof in the paragraph, and the paragraph will have a clear point of view supporting the claim. 2) There can be instances where direct correlation to the claim is not available. Make use of the sentences in the paragraph to provide a corresponding output supporting the claim. 3) The explanation should be at least one and at most twelve sentences long.\nQ: Paragraph: On 10 June 2016, the Daily Beast reported that Sen. David Perdue urged attendees of the Faith & Freedom Coalition’s Road to Majority conference to pray for misfortune and death to befall President Barack Obama: At a major event for conservative Christians this morning, a Republican senator joked about praying for President Obama’s “days to be short.” Sen. David Perdue, a freshman senator from Georgia, opened his remarks at the Faith & Freedom Coalition’s Road to Majority conference by encouraging attendees to pray for President Obama. But, he added in a joking tone, they need to pray for him in a very specific way: “We should pray for him like Psalms 109:8 says: Let his days be few, and let another have his office,” the senator said, smiling wryly. The crowd chuckled and he moved on with his address. The rest of that passage, which Perdue did not recite, reads, “May his children be fatherless and his wife a widow. May his children be wandering beggars; may they be driven from their ruined homes.” The psalm is a pointed, lengthy death wish for one of David’s enemies. Video depicted Purdue’s 10 June 2016 remarks: Psalms 109:8 (alternately named “Song of the Slandered”) was rendered in the manner below in the King James Bible: Hold not thy peace, O God of my praise; For the mouth of the wicked and the mouth of the deceitful are opened against me: they have spoken against me with a lying tongue. They compassed me about also with words of hatred; and fought against me without a cause. For my love they are my adversaries: but I give myself unto prayer. And they have rewarded me evil for good, and hatred for my love. Set thou a wicked man over him: and let Satan stand at his right hand. When he shall be judged, let him be condemned: and let his prayer become sin. Let his days be few; and let another take his office. Let his children be fatherless, and his wife a widow. Let his children be continually vagabonds, and beg: let them seek their bread also out of their desolate places. Let the extortioner catch all that he hath; and let the strangers spoil his labour. Let there be none to extend mercy unto him: neither let there be any to favour his fatherless children. Let his posterity be cut off; and in the generation following let their name be blotted out. Let the iniquity of his fathers be remembered with the LORD; and let not the sin of his mother be blotted out. Let them be before the LORD continually, that he may cut off the memory of them from the earth. As many pointed out, the Senator’s Biblical reference wasn’t a new or even uncommon scripture-based jab at President Obama. A 2009 article reported that the verse was traction across the internet as a veiled threat cloaked in the guise of prayerful intent: There’s a new slogan making its way onto car bumpers and across the Internet. It reads simply: “Pray for Obama: Psalm 109:8” A nice sentiment? Maybe not. The psalm reads, “Let his days be few; and let another take his office.” Presidential criticism through witty slogans is nothing new. Bumper stickers, t-shirts, and hats with “1/20/09” commemorated President Bush’s last day in office. But the verse immediately following the psalm referenced is a bit more ominous: “Let his children be fatherless, and his wife a widow.” The slogan comes at a time of heightened concern about antigovernment anger. Earlier this year, the president’s senior adviser, David Axelrod, said that Tea Parties could lead to something unhealthy. In September, authorities shut down a poll on Facebook asking if President Obama should be killed. Still, that doesn’t push the Psalms citation into the realm of hate speech, says Chris Hansen, a staff attorney with the American Civil Liberties Union (ACLU). That particular piece was published during President Obama’s first term in office. Some argued at the time that the reference to the verse simply expressed a hope that he not be re-elected to a second term: Deborah Lauter, director of civil rights at the Anti-Defamation League agrees that the bumper sticker falls within acceptable political discourse. “The problem is you don’t know if people who are donning that message in a shirt or on a bumper sticker are fully aware of the quote or what follows. Obviously that message makes the ambiguity disappear. If they’re just referring to him being out of office, that’s one thing. If they’re referring to him being dead, that’s so offensive. It’s protected speech, but it’s clearly offensive.” However, that motive ceased to be relevant after Obama’s 2012 re-election. A representative for the Senator provided a terse statement to a Bloomberg reporter about the controversy: David Perdue spokeswoman Caroline Vanvick responds in an email: “He in no way wishes harm towards our president” pic.twitter.com/PPj5jtZv0n — Sahil Kapur (@sahilkapur) June 10, 2016 The statement read: Senator Perdue said we are called to pray for our country, for our leaders, and for our president. He in no way wishes harm towards our president and everyone in the room understood that. However, we should add the media to our prayer list because they are pushing a narrative to create controversy and this is exactly what the American people are tired of. It is true Sen. David Perdue laughed and referenced Psalms 109:8 during a 10 June 2016 conservative Christian event. A representative for the Senator addressed the ensuing controversy, blaming the media for “pushing a narrative” for the outcry. Claim: Sen. David Perdue advised attendees to offer up an ominous prayer aimed at President Obama during the 2016 Faith & Freedom Coalition’s Road to Majority conference.\nA: " }, { "from": "gpt", "value": "What's true: Sen. David Perdue referenced Psalms 109:8 at an event; Perdue's representative later denied he wished death on the President. What's false: Sen. Perdue didn't explicitly state attendees at the conference should pray expressly for the President to die." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task, you are given a hateful post in English from online platforms. You are expected to classify the post into two classes: aggresive or non-aggresive. An aggresive post is one that expresses feelings and opinions in an abusive way and tries to dominate others. Note that the URLs in the text have been replaced with [Link].\nTeacher: Now, understand the problem? Solve this instance: Post: @dcexaminer Even a Gym wouldnt hire him, and who da heck got him in DC? #MAGA #WalkAway #LeaveDNC #VoteRed2018 #Trump2020 #TrumpPence2020 #WakeUp #NoJihad #NoDACA\nStudent:" }, { "from": "gpt", "value": "Non-aggresive" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Q: A text is given in English. Translate it from the English language to the Telugu language. The translation must not omit or add information to the original sentence.\nThe signing of Memorandum of Understanding with Bulgaria will be instrumental in increasing arrival from this important source market.\nA:" }, { "from": "gpt", "value": "భార‌త‌దేశానికి ఒక చ‌క్క‌టి ప‌ర్య‌ట‌క విప‌ణి అయిన బ‌ల్గేరియా తో అవ‌గాహ‌న పూర్వ‌క ఒప్పందం పై సంత‌కాలు చేయ‌డం ఆ దేశం నుండి భార‌త‌దేశానికి వ‌చ్చే పర్యటకుల సంఖ్య ను పెంచుకొనే అవకాశం అందిరానుంది." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: You are given a sentence in Persian. Your job is to translate the Farsi sentence into Italian.\nInput: در اکتبر سال ۱۹۰۳ ، نظر غالب متخصصان ایرودینامیک نظر غالب متخصصان ایرودینامیک این بود که شاید ۱۰ میلیون سال بعد ، ما بتوانیم ماشینی بسازیم که پرواز کند. این بود که شاید ۱۰ میلیون سال بعد ، ما بتوانیم ماشینی بسازیم که پرواز کند.\nOutput:" }, { "from": "gpt", "value": "Nell'ottobre del 1903 l'opinione prevalente degli esperti di aerodinamica riteneva che forse, a 10 milioni di anni di distanza, avremmo costruito un apparecchio che avrebbe volato." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task, you get an English sentence and a corresponding Spanish translation of the English sentence. Your task is to return a \"Yes\" if the translation is correct, otherwise return \"No\"\nProblem:English: Big expectations are built up for these reforms both within the Commission and outside. \n Spanish:Doy las gracias a mis colegas por concederme generosamente tiempo para mi intervención.\nSolution:" }, { "from": "gpt", "value": "No" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given a sentence in Persian. Your job is to translate the Farsi sentence into Arabic.\n\nو آنگاه آنها کُد می نوشتند ، معمولا کُد های ماشینی ، و گاهی کُد های صفر و یکی ، که سپس با پست به مرکز داده ها فرستاده می شد که روی چسب کاغذی یا کارتی منگنه شود و بعد دوباره حک شود تا مورد بازبینی قرار گیرد.\nSolution: وقد كتبن اللغة وغالبا ما كانت لغة آلة وأحيانا شفرة ثنائية ترسل بعدها بالبريد لمركز البيانات لتنقل على شريط أو بطاقة ورقية مثقبة ثم تعاد الكرة مرة أخرى للتأكد.\nWhy? The Farsi sentence is correctly translated into Arabic, because the meaning is preserved.\n\nNew input: پس بیایید یک دقیقه به آن فکر کنیم.\nSolution:" }, { "from": "gpt", "value": "لذلك ، دعونا نفكر في ذلك لمدة دقيقة." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Q: Given a sentence in the Japanese and Thai language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".\nJapanese: イスラエル軍はこの新たな船隊を「全小型船隊の母」と呼んでいる。 \n Thai: กองทัพอิสราเอลได้ขนานนามบรรดาเรือกองใหม่นี้ว่า \"มารดาแห่งกองเรือรบทั้งปวง\"\nA:" }, { "from": "gpt", "value": "Yes" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Galician. Your job is to translate the Galician sentence into English.\nProblem:Esta aspiración é enormemente poderosa.\nSolution:" }, { "from": "gpt", "value": "This aspiration that our healthcare keep us healthy is an enormously powerful one." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given a sentence which is either in the Hindi language or English language. You task is to identify the language of input sentence. Input sentence can be in Hindi or English language only and also it cannot have two languages at a time.\n\nInput: Consider Input: लेकिन मैं इस बात का कायल हूं कि इंग़्लैंड में या और कहीं पुराना उदारवादी दृष्टिकोण अब काम लायक नहीं रह गया है ।\n\nOutput: Hindi\n\n\nInput: Consider Input: कल्पना जी मार्च १९९५ में नासा के अंतरिक्ष यात्री कोर में शामिल हुईं और उन्हें १९९८ में अपनी पहली उड़ान के लिए चुना गया था।\n\nOutput: Hindi\n\n\nInput: Consider Input: The state Archaeological Department gets a paltry Rs 10 lakh as annual allocation to look after three of the 27 forts under its purview-Simhagad , Rajgad and Torna .\n\n" }, { "from": "gpt", "value": "Output: English\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "TASK DEFINITION: In this task, you will be shown an extract from a movie plot. You need to read the extract and create questions that can be answered from the extract. Once you create a question you also need to provide the correct answer for it. Write your answer like \"Question: your question, Answer: your answer\". The questions should be well-formed and grammatically correct. The questions should be completely answerable from the given passage and should not require any external knowledge. Subjective questions are not allowed. Short answers containing words that are present in the passage are preferred. Create questions that result in factoid answers. A simple rule of thumb to decide whether a question is a factoid or not is to see if two different people with average reading/comprehension skills would come up with the same answer after reading the passage.\nPROBLEM: Dr. Frederick Frankenstein (Gene Wilder) is a respected lecturer at an American medical school and is more or less happily (though blandly) engaged to the tightly wound Elizabeth (Madeline Kahn). Frederick becomes exasperated when anyone brings up the subject of his grandfather, the famous mad scientist, to the point of insisting that his name is pronounced \"Fronk'-en-steen\".A solicitor informs Frederick that he has inherited his family's estate. Traveling to said estate in Transylvania, Frankenstein meets his comely new lab assistant Inga (Teri Garr), along with the household servants Frau Blücher (Cloris Leachman) and Igor (Marty Feldman) (who, after hearing Frederick claim his name is pronounced \"Fronkensteen\" counter-claims that his is pronounced \"Eye'-gor.\")Inga assists Frederick in discovering the secret entrance to his grandfather's laboratory. Upon reading his grandfather's private journals the doctor is inspired to resume his grandfather's experiments in re-animating the dead. He and Igor successfully exhume and spirit away the enormous corpse of a recently executed criminal, but Igor's attempt to steal the brain of a revered scientist from the local \"brain depositary\" goes awry, and he takes one labeled, \"Do Not Use This Brain! Abnormal\" instead.The doctor and reassembled monster (Peter Boyle) are elevated on a platform to the roof of the laboratory during a lightning storm. The experimenters are first disappointed when the electrically charged creature fails to come to life, but the reassembled monster eventually revives. The doctor assists the monster in walking but, frightened by Igor lighting a match, it attacks Frederick and must be sedated.Meanwhile, the local townspeople are uneasy at the possibility of Frederick continuing his grandfather's work. Most concerned is Inspector Kemp (Kenneth Mars), who visits the doctor and subsequently demands assurance that he will not create another monster. Upon returning to the lab, Frederick discovers that Frau Blücher is setting the creature free. After she reveals the monster's love of music, and her own romantic relationship with Frederick's grandfather, the creature is enraged by sparks from a thrown switch, and escapes from the Frankenstein castle.While roaming the countryside, the Monster has frustrating encounters with a young girl and a blind hermit (cameo by Gene Hackman); these scenes directly parody ones from the original Frankenstein movies. Frederick recaptures the monster, wins him over with flattery, and finally fully acknowledges his heritage.After a period of training, he offers a theater full of illustrious guests the sight of \"The Creature\" following simple commands. The demonstration continues with Frederick and the Monster launching into the musical number \"Puttin' on the Ritz\", complete with top hats and tails (and no small amount of clumsiness on the monster's part), which ends disastrously when a stage light explodes and frightens the monster. He becomes enraged and charges into the audience where he is captured and chained by police.After being tormented by a sadistic jailer who smiles, the Monster escapes again, then kidnaps and ravishes the not-unwilling Elizabeth when she arrives unexpectedly for a visit. Elizabeth falls in love with the creature due to his inhuman stamina and his enormous penis.The townspeople, led by Inspector Kemp, hunt for the Monster. Desperate to get the creature back and correct his mistakes, Frederick plays music and lures the Monster back to the castle. Just as the Kemp-led mob storms the laboratory, Dr. Frankenstein transfers some of his stabilizing intellect to the creature who, as a result, is able to reason with and placate the mob.The film ends happily, with Elizabeth married to the now erudite and sophisticated Monster, while Inga joyfully learns what her new husband Frederick got in return from the Monster during the transfer procedure (the Monster's gigantic penis).\n\nSOLUTION: Question: Where does Dr Frederick Frankenstein work ?, Answer: Dr. Frederick Frankenstein is a respected lecturer at an American medical school.\n\nPROBLEM: Dr Paul Carruthers [Bela Lugosi] appears to all of Heathville as a kindly doctor and research scientist for Heath-Morton Cosmetics, Ltd. But in his secret laboratory, Carruthers is actually conducting personal experiments--one of which is a formula for an oriental shaving lotion; another is the creation of a giant bat who hates the smell of the lotion. Bitter because founding fathers Martin Heath [Edward Mortimer] and Henry Morton [Guy Usher] got rich on his formulas while he himself is awarded with menial bonuses, Carruthers plans to sic his giant bat on their families.First to go is Roy Heath [John Ellis]. Investigative reporter Johnny Layton [Dave O'Brien] and cameraman 'One Shot' McGuire [Donald Kerr] of the Chicago Register are sent to snoop for a story. The only clues are the victim's neck wounds that look like they were made by the beak and talons of a bird, a peculiar faint odor about the wounds, and some mouse or bat hairs. That afternoon, Layton and McGuire have tea with Carruthers and Martin's daughter Mary [Suzanne Kaaren], and Layton and Mary become smitten with each other. Mary invites Layton to come back to the estate that evening.That evening, Johnny sees Martin's son Tommy [Alan Baldwin] attacked in the garden by a giant bat. When Don Morton [Gene O'Donnell], son of the other founding father, Henry Morton, is subsequently killed in the same way, Layton finds a bottle of shaving lotion of the same scent discovered on all the bodies. In an attempt to provide a picture of the 'devil bat', McGuire photographs a fake bat which is proven fraudulent by a scientist on a talk radio program. Layton and McGuire are fired by their paper, but they stay in Heathville to get to the bottom of the story. They trace the lotion to Carruthers and interview him in an attempt to expose him, but he readily admits to creating the formula. He even gives Layton a bottle to try. That night, Layton and McGuire are dive-bombed by the giant bat, which Layton kills. The size of the bat has scientists marvelled, and Layton and McGuire are exonerated and rehired.Carruthers creates a new devil bat and sics it on Henry Morton. That night a giant bat attempts to get into Mary's bedroom, and it is learned that someone has switched her perfume with formula. While Carruthers tends Mary, Layton visits his laboratory. He waits for Carruthers to return and follows him into his secret lab where Carruthers releases the devil bat. Layton asks Carruthers for a bottle of the lotion and informs him that he intends to sit in the garden and hopefully attract the bat with it. Layton even invites Carruthers to watch, but he splashes lotion on Carruthers and the bat ultimately kills Carruthers. [Original synopsis by bj_kuehl.]\n\nSOLUTION: Question: Why is Lugosi upset?, Answer: Because the founding fathers took the fame for the fortune\n\nPROBLEM: In the opening scene, a helmeted racer leads a gang of stunt drivers who hijack a shipment of electronics from a moving truck.Brian O'Conner (Brian Walker) is an undercover police officer, driving supercharged cars and trying to infiltrate Dominic Toretto's (Vin Diesel) gang, who are suspects in the robberies. He first visits Dominic's cafe, where he makes conversation with Dominic's younger sister, Mia (Jordana Brewster) and tries to make inroads with the gang by selling performance equipment. Vince (Matt Schulze) is jealous, and a fight breaks out. His girlfriend Letty (Michelle Rodriguez) begs Dom to break it up, who does so, threatening to get Brian fired.That night, racers gather for street racing. Brian meets Hector (Noel Gugliemi), and they wait for Dom. Brian offers his car in a bet, and Dom's tech Jesse (Chad Lindberg) checks his car out. The spectators line the streets, lighting the way. Brian and Dom race with Johnny Tran (Rick Yune) and Edwin (Ja Rule). Dom wins, showing Brian superior driving and timing. The racers pick up a police alert on the scanner, and everyone flees. Dom parks his car and flees on foot, and Brian helps him escape. Dom has researched Brian (getting his cover story), but as they chat, they are surrounded by uzi-wielding Chinese bikers, who escort them to an empty lot. The leader of this gang, Johnny Tran, admires Brian's car and refers to a race in the desert next month. He and his goons shoot up Brian's car, which explodes from the NOS (Nitrous Oxide) on board.Back at Dom's house, a party is in progress. Dom yells at his gang, saying Brian was the only one to help him. Vince is upset that Brian is back, and Mia breaks up with him.The next day Brian's boss, Sgt. Tanner (Ted Levine), briefs Brian. Truckers are getting nervous about the robberies, and the FBI are now involved. They keep hearing about modified Honda Civics in the robberies. Brian brings Dom a wrecked Toyota Supra with a powerful engine, and starts working in Dom's garage. Vince continues to be angry with Dom's friendship with Brian, and Mia teases him.The next day, Hector buys parts for Honda Civics from Brian, and Brian gets suspicious. He breaks into Hector's garage, but Vince and Dom have followed him. Brian convinces them he's spying on the competition for Race Wars next month. Vince is suspicious, but Dom thinks it's a good idea, and they break into Tran's garage. Brian spots possible stolen goods. Tran and his goons arrive, and Dom, Brian and Vince watch as they torture local fence Ted (Beau Holden) about stolen engines.Brian tells the FBI, but wants to resist moving in on Tran until they have more evidence. His boss thinks he's too soft on Torretto; that Brian is going \"native\".The next day, Dom takes Brian into confidence and shows off his supercharged 1970 Dodge Charger, one he never drives. Dom says it has too much power.Over dinner, Brian and Mia talk about Dom, then Mia shows off her driving skills. At the same time, another robbery is in progress, and Brian gets a call from his boss that they are moving in on Tran in the morning. The raid goes off with Brian wearing a hood (to avoid recognition), but Tran's gang gets out for lack of evidence - the suspicious goods were purchased. Sgt. Tanner cautions Brian about falling for Mia, and tells him Dominic is the next suspect.The next day, Brian and Dom take the rebuilt Supra for a spin, and smoke a Ferrari. Over lunch, Brian asks to get in on Dom's next job, but Dom wants to see how Brian does at Race Wars first.In the middle of the desert, Race Wars begins. Letty wins, but Jesse loses his car to Tran and refuses to pay. Tran accuses Dom of being an informer as a result of the police raid on his place the day before, and a fight breaks out.That night, Mia is upset with Dom, who is obviously going on another robbery (revealing that Dom and his gang really are the hijackers that Brian is trying to nail all along). Brian confesses that he's a cop, and asks Mia to help him warn Dom about the truckers arming themselves and the FBI operations. Brian calls for a trace of Dom's cell phone. Letty is nervous about the upcoming job, but they go ahead with it.At the climax, Dom and his gang don their masks and cars and set out for another hijacking job. The robbery begins to go wrong when Vince jumps on the truck, but is shot at by the trucker. Letty crashes her car, and Leon (Johnny Strong) rescues her. Brian arrives on the scene and risks his life to save Vince as the trucker reloads his shotgun. Dom arrives and hears Brian calling for a medical helicopter, identifying himself as a cop. Dom is stunned, but Vince is the first priority. After Vince is stabilized, Dom storms off with Mia following.Back at Dom's house, Brain confronts Dom. Jesse returns, and Tran shoots him in a drive-by. Brian gives chase, and Dom gets in the Charger to pursue as well. Dom stops in front of one of the motorcycles, sending the goon into a field, and Brian shoots Tran. Brian sees Dom fleeing, and pursues in the Supra. They race, and Dom's car begins destroys itself from the massive torque in the motor. They finish the race, but Dom hits a truck pulling out from a side street. The Charger is wrecked, and Dom is injured. As the police sirens are heard in the distance, Brian gives Dom his car and Dom escapes.\n\nSOLUTION:" }, { "from": "gpt", "value": "Question: What is the name of the undercover police officer?, Answer: Brian O'Connor\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nThis task is about classifying the similarity of two sentences. The sentences can be classified as (a) SIMILAR - similar to each other, and (b) DISSIMILAR - not similar to each other. Sentences that have the same RDF relationship in terms of [subject, predicate, object] are similar to each other. The input is a list of two sentences and the output is either SIMILAR or DISSIMILAR.\n\n['piątek is the word for Friday in Polish', 'You say Friday in Polish by piątek.']\nSolution: SIMILAR\nWhy? The classified label of this sentence is a good example since both the sentences share the same RDF structure [['Polish', 'FRIDAY_FIFTH_DAY', 'piątek']] and are essentially conveying the same thing.\n\nNew input: ['The first club Jens Härtel played for was FC Lokomotive Leipzig. He also played for RB Leipzig and was the manager of 1 FC Magdeburg.', 'Jens Härtel is in the RB Leipzig club, started with FC Lokomotive Leipzig and has managed 1 FC Magdeburg.']\nSolution:" }, { "from": "gpt", "value": "SIMILAR" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: Given a sentence in the Japanese, provide an equivalent translation in Filipino that retains the same meaning through the translation. In translation, keep numbers as it is.\nInput: このテロ事件での死者数は、それまでに英国で起こったどのテロよりもより大きな被害だった。\nOutput:" }, { "from": "gpt", "value": "Ang bilang ng namatay para sa insidente ng terorista ay mas malaki kaysa sa iba na nangyari sa United Kingdom kamakailan." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nThe input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the self-need strategy, otherwise output No. self-need is a selfish negotiation strategy. It is used to create a personal need for an item in the negotiation, such as by pointing out that the participant sweats a lot to show preference towards water packages.\n\nContext: 'That sounds pretty reasonable as I am in need of firewood the most. Would it be most reasonable to each take what we need most and split the water down the middle?' 'Yes, it would.' 'I think that sounds fair. The problem is that there are 3 waters and one of us would get two and the other one. How should we sort that?'\nUtterance: 'You can take the two water. I am not that thirsty most days.'\nSolution: No\nWhy? In this utterance, the participant does not use self-need since they do not talk about any need for themselves.\n\nNew input: Context: 'I can give you 2 packages of water. I think there is plenty of water, so I do not need extra water.🙂' 'What are you going to use your water for? And thank you.' 'In case I do no feel like going to other places to get water. It would be nice to have extra water.'\nUtterance: 'I see, and do you have a way to bring the water with you?'\nSolution:" }, { "from": "gpt", "value": "No" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Japanese.\nProblem:כבר לא נראיתי כמו הודי.\nSolution:" }, { "from": "gpt", "value": "こうなるとインド人には見えません" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Galician. Your job is to translate the Galician sentence into Polish.\nQ: Parece unha hamburguesa xigante.\nA:" }, { "from": "gpt", "value": "To wygląda jak gigantyczny hamburger." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a statement in Croatian, a question word and four choices in Croation. If the question word is \"cause\", you should choose the option that is most likely to be the cause of the statement. If the question word is \"effect\", you should pick the choice that is most likely to be a consequence of the statement. Write the exact text of the choice, not the number.\n\nStatement: Grad je ponovno izabrao gradonačelnika.\nQuestion: cause\nChoice 1: Gradonačelnik je ispunio svoja obećanja.\nChoice 2: Pao je u bazen.\nChoice 3: Grad je smanjio svoj budžet.\nChoice 4: Počela je zaboravljati.\nGradonačelnik je ispunio svoja obećanja.\n\nStatement: Djevojka je zaželjela želju.\nQuestion: cause\nChoice 1: Ugledala je crnu mačku.\nChoice 2: Prodao je svoju imovinu.\nChoice 3: Postavljao joj je pitanja o njoj.\nChoice 4: Ugledala je zvijezdu padalicu.\nUgledala je zvijezdu padalicu.\n\nStatement: Skupina je zanemarila ženinu pogrešku.\nQuestion: effect\nChoice 1: Moja je susjeda otišla iz svoje kuće.\nChoice 2: Film je počeo.\nChoice 3: Žena se ispričala.\nChoice 4: Žena je odahnula.\n" }, { "from": "gpt", "value": "Žena je odahnula.\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "TASK DEFINITION: In this task, you will be presented with an English sentence, and you have to translate it into Arabic.\nPROBLEM: And we thank you in advance for your thoroughness in the matter.\n\nSOLUTION: ونحن نشكرك مقدما على تدقيقك في المسألة\n\nPROBLEM: But OMTs also fit well with a large body of historicalevidence that, in times of crisis, policymakers must focus onextinguishing the fire, rather than negotiating over who owns thewater and what its cost should be.\n\nSOLUTION: ولكن برنامج المعاملات النقدية الصريحة يتناسب بشكل كبير مععدد هائل من الأدلة التاريخية التي تشير إلى ضرورة تركيز صناع القرارالسياسي في أوقات الأزمات على إطفاء الحرائق بدلاً من التفاوض على منيملك المياه وكم ينبغي أن تكون تكلفتها.\n\nPROBLEM: Issue of communiqués concerning closed meetings 159 103.\n\nSOLUTION:" }, { "from": "gpt", "value": "102- إصدار بلاغات إعلامية بشأن الجلسات المغلقة 175\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer.\nProblem:Traitor Edward Snowden has revealed he did not read all the top-secret intelligence documents he leaked – a move which put lives at risk from terrorists. In a television interview the fugitive squirmed as he admitted only ‘evaluating’ the files stolen from GCHQ and the US National Security Agency. The former US spy also acknowledged there had been a ‘f***-up’ when newspapers that were handed the classified material failed to redact sensitive details exposing operations against Al Qaeda. Scroll down for video Last Week Tonight host John Oliver flew to Moscow to grill Edward Snowden about the leaking of 'harmful' documents and asks him to explain why he did itBritish comedian travelled to Moscow to interview the whistleblowerQuestions why the former CIA systems administrator leaked the filesGets him to explain the security threat in the context of nude picturesDescribes Snowden as America's most famous 'hero and/or traitor'Snowden, at moments, is stunned into silence by the line of questioning \n Question:_ (cuts in sarcastically): Right, because when you’re handing over thousands of NSA documents, the last thing you want to do is read them.\nSolution:" }, { "from": "gpt", "value": "Edward Snowden" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a question in English, and your task is to translate it into Persian.\n\nIs anything wrong with being an atheist?\nOutput:" }, { "from": "gpt", "value": "آیا بی دین بودن اشتباه است؟" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given a sentence, an entity and its sentiment towards the entity, verify if it is the correct sentiment towards the entity. Answer should be yes or no. Note that URLs in the text have been replaced with [Link].\n\nVerify if the sentiment of the following document towards the entity Mark Richt is Negative . \"It was a shame in my opinion but I’m probably not supposed to say that \" Richt said." }, { "from": "gpt", "value": "yes" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: political or non-political depending on the topic.\nExample: খানকির পুলা মালায়নদের মেরে সাফা করে ফেল\nOutput: political\nHere it expresses hate against the government, hence tagged as political.\n\nNew input case for you: কোরবানির হাটে বারি খেয়ে। বালের কনটেন্ট বানায়। হিজরায় \nOutput:" }, { "from": "gpt", "value": "non-political" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a set of context paragraphs, some supporting facts and an answer of a question. Your task is to generate question for given answer based on set of context paragraphs, supporting facts and an answer.\nSee one example below:\nProblem: Context_1 : Charles Edward Ives ( ; October 20, 1874May 19, 1954) was an American modernist composer. He is one of the first American composers of international renown, though his music was largely ignored during his life, and many of his works went unperformed for many years. Over time, he came to be regarded as an \"American original\". He combined the American popular and church-music traditions of his youth with European art music, and was among the first composers to engage in a systematic program of experimental music, with musical techniques including polytonality, polyrhythm, tone clusters, aleatory elements, and quarter tones, foreshadowing many musical innovations of the 20th century. Context_2 : Daniel Evan Freeman (born 27 April 1959) is an American musicologist who specializes in European art music of the eighteenth century, in particular the musical culture of eighteenth-century Prague and the Bohemian lands. He is also active as a pianist and music editor. Context_3 : Art music (also known as Western classical music, cultivated music, serious music, canonic music, and more flippantly, real music or normal music) is an umbrella term that refers to musical traditions, implying advanced structural and theoretical considerations and a written musical tradition. \"Serious\" or \"cultivated\" music are terms frequently used as a contrast for ordinary, everyday music (popular and folk music, also called \"vernacular music\"). After the 20th century, art music was divided into two extensions: \"serious music\" and \"light music\". Context_4 : In the history of European art music, the term \"common practice period\" refers to the era between the formation and the dissolution of the tonal system. Though there are no exact dates for this phenomenon, most features of the common-practice period persisted from the mid to late baroque period, through the Classical and Romantic periods, or roughly from around 1650 to 1900. While certain prevailing patterns and conventions characterize the music of this period, the time period also saw considerable stylistic evolution. Some conventions evolved during this period that were rarely employed at other times during what may still be labeled \"common practice\" (for example, Sonata Form). Thus, the dates 1650–1900 are necessarily nebulous and arbitrary borders that depend on context. The most important unifying feature through this time period concerns a harmonic language to which modern music theorists can apply Roman numeral analysis. Context_5 : The Festival Oude Muziek Utrecht (\"Utrecht Early Music Festival\") is an annual music festival that showcases and celebrates early European art music. The ten-day festival takes place in the Dutch city of Utrecht, and begins in August. The programme comprises concerts, activities, lectures, exhibitions, and a symposium. Context_6 : Assaf Shelleg (Hebrew: אסף שלג‎ ‎ ), is a musicologist and pianist, a senior lecturer of musicology at The Hebrew University of Jerusalem. He was previously the Schusterman Visiting Assistant Professor of Musicology and Jewish Studies in the Department of Religious Studies at the University of Virginia (2011–14), and had taught prior to that as the visiting Efroymson Scholar in the Jewish, Islamic & Near Eastern Languages and Cultures Department at Washington University in St. Louis (2009–11). Shelleg specializes in twentieth-century Jewish and Israeli art music and has published in some of the leading journals in both musicology and Israel Studies on topics ranging from the historiography of modern Jewish art music to the theological networks of Israeli art music. Shelleg's book, \"Jewish Contiguities and the Soundtrack of Israeli History\", appeared in November 2014 with Oxford University Press. The book studies the emergence of modern Jewish art music in central and Western Europe (1910s-1930s) and its translocation to Palestine/Israel (1930s-1970s), exposing the legacies of European antisemitism and religious Judaism in the making of Israeli art music. Moving to consider the dislocation of modern Jewish art music the book examines the paradoxes embedded in a Zionist national culture whose rhetoric negated its pasts, only to mask process of hybridizations enchained by older legacies. \"Jewish Contiguities\" has won the 2015 Engle Prize for the study of Hebrew Music, and the 2016 Jordan Schnitzer Book Award. Context_7 : Vocal harmony is a style of vocal music in which a consonant note or notes are simultaneously sung as a main melody in a predominantly homophonic texture. Vocal harmonies are used in many subgenres of European art music, including Classical choral music and opera and in the popular styles from many Western cultures ranging from folk songs and musical theater pieces to rock ballads. In the simplest style of vocal harmony, the main vocal melody is supported by a single backup vocal line, either at a pitch which is above or below the main vocal line, often in thirds or sixths which fit in with the chord progression used in the song. In more complex vocal harmony arrangements, different backup singers may sing two or even three other notes at the same time as each of the main melody notes, mostly with consonant, pleasing-sounding thirds, sixths, and fifths (although dissonant notes may be used as short passing notes). Context_8 : David Wallis Reeves (February 14, 1838 – March 8, 1900), also known as D. W. Reeves or Wally Reeves, was an American composer, cornetist, and bandleader. He developed the American march style, later made famous by the likes of John Philip Sousa, and his innovations include adding a countermelody to the American march form in 1876. Sousa called Reeves \"The Father of Band Music in America\", and stated he wished he himself had written Reeves' \"Second Regiment Connecticut National Guard March\". Charles Ives also borrowed from the \"Second Connecticut\" on four occasions. Context_9 : \"Indian classical music is one of many forms of art music that have their roots in particular regional cultures. For other \"classical\" and art music traditions, see List of classical and art music traditions.\" Context_10 : Progressive music is music that subverts genre and expands stylistic boundaries outwards. Rooted in the idea of a cultural alternative, musical progressiveness embodies a continuous move between explicit and implicit references to genres and strategies derived from various cultural domains, such as European art music, Celtic folk, West Indian, or African. The word \"progressive\" comes from the basic concept of \"progress\", which refers to development and growth by accumulation, and is often deployed in numerous music genres such as progressive country, progressive folk, progressive jazz, and (most significantly) progressive rock. fact_1 : Charles Ives also borrowed from the \"Second Connecticut\" on four occasions. fact_2 : Charles Edward Ives ( ; October 20, 1874May 19, 1954) was an American modernist composer. fact_3 : He combined the American popular and church-music traditions of his youth with European art music, and was among the first composers to engage in a systematic program of experimental music, with musical techniques including polytonality, polyrhythm, tone clusters, aleatory elements, and quarter tones, foreshadowing many musical innovations of the 20th century. Answer: 1874May\nSolution: What is the birthyear of the American composer that borrowed from \"Second Connecticut\" on four occasions and combined American popular and church-music traditions with European art music?\nExplanation: From the fact_1 from context _8, and fact _2 and fact _3 from context _1, we can arrive at 1874 May which is accurate answer of generated question.\n\nProblem: Context_1 : Skeid Fotball is a Norwegian football club and is located in the capital Oslo. Its current home field is Nordre Åsen, after the club stopped playing at Bislett after the 2012 season. In past decades it has gained a reputation as a talent factory for the larger clubs in Norwegian football, and it has produced several players for the national team such as Daniel Braaten, Daniel Fredheim Holm, Omar Elabdellaoui and Mohammed Abdellaoue. Other notable players include Paul Miller. Skeid played in Adeccoligaen in 2009 after a short stint in the second division. They finished champions of the Second Group of Norwegian Second Division in 2008. However, Skeid relegated again to Second Division at end of 2009 season in 16th and last position despite a good start. Context_2 : R.S.C. Anderlecht is a professional football team from Brussels, Belgium. The club was founded in 1908 and holds the record of Belgian championship titles. Players listed in this article are players who played in at least 100 games in the Belgian first division. The recordman of appearances in the first division for RSC Anderlecht is legendary player Paul Van Himst with 457 matches between 1960 and 1975. Joseph Mermans, nicknamed \"Le Bombardier\" (English: The Bomber ) is RSC Anderlecht record goalscorer with 338 goals in 384 matches, between 1942 and 1957. Dutch international Rob Rensenbrink, who scored 141 goals in 261 league appearances for Anderlecht between 1971 and 1980 was voted the club's greatest ever player in 2008. Context_3 : Lazarus Shiimi, known by his stage name Gazza, is one of the most commercially successful and best selling recording artists in Namibia. Gazza was born on 10 March 1977 in Oshakati (North of Namibia) in a family of seven. At that time, he had to live in a shack behind someone's house after his father died. Despite those modest beginnings, he has always pursued the goals he had set for his life. Gazza has always loved challenges. As a soccer lover, he nicknamed himself Gazza after famous English soccer player Paul Gascoigne. Context_4 : Paul A. Johnson (born 26 June 1984) is an Australian rules footballer currently listed with the East Perth Football Club in the West Australian Football League (WAFL). He previously played senior matches with the West Coast Eagles, the Melbourne Football Club, and the Hawthorn Football Club in the Australian Football League (AFL), the Swan Districts Football Club in the WAFL, and the Sandringham Football Club and the Box Hill Football Club in the Victorian Football League (VFL). Johnson was the winner of the 2005 J. J. Liston Trophy, as well as the 2012 Simpson Medal as the best player in an interstate match for Western Australia. Context_5 : Wayne Mark Rooney ( ; born 24 October 1985) is an English professional footballer who plays for Premier League club Everton. He has played much of his career as a forward, and he has also been used in various midfield roles. He is the record goalscorer for the England national team and for Manchester United. At club level, he has won every honour available in English, Continental and European football, with the exception of the European Super Cup. Along with Michael Carrick, he is the only English player to win the Premier League, FA Cup, UEFA Champions League, League Cup, UEFA Europa League and FIFA Club World Cup. Context_6 : Tottenham Hotspur Football Club, commonly referred to simply as Tottenham ( ) or Spurs, is an English football club located in Tottenham, Haringey, London, that competes in the Premier League. The club's home for the 2017–18 season will be Wembley Stadium, as their former home of White Hart Lane is being dismantled to make way for a completely new rebuilt stadium on the same site. Their newly developed training ground is in Bulls Cross on the northern borders of the London Borough of Enfield. Context_7 : Paul Miller (born 31 January 1968 in Woking) is an English retired football forward. Miller notably played in the Premier League for Wimbledon during the 1993-94 season. Context_8 : My Old Man song is a football song sung by fans of English and Northern Irish Association football clubs. It was first used by Aston Villa fans and continues to be used, to the extent that many teams have copied the Villa fans chant, along with their 'It's your round chant' which celebrates the iconic ex player Paul McGrath. Usage has declined in recent years as the aspects of hooliganism it depicts has also decreased. Context_9 : Human Remains was an American grindcore band, formed in 1989 in New Jersey. The band featured the vocalist Paul Miller, the guitarists Steve Procopio and James Baglino, as well as the drummer Dave Witte, who is also known for his work for Discordance Axis, Burnt by the Sun, and Atomsmasher. The band's most notable release, \"Using Sickness as a Hero\" EP, was released by Relapse Records in 1996. A compilation album featuring the band's entire discography, \"Where Were You When: 1989-1995\", was also released in 2002. Context_10 : Paul Richard Miller (born 11 October 1959) is an English former footballer who played in the Football League for Tottenham Hotspur, Charlton Athletic, Watford, Bournemouth, Brentford and Swansea City. Miller's favoured position was centre back. fact_1 : Paul Richard Miller (born 11 October 1959) is an English former footballer who played in the Football League for Tottenham Hotspur, Charlton Athletic, Watford, Bournemouth, Brentford and Swansea City. fact_2 : Tottenham Hotspur Football Club, commonly referred to simply as Tottenham ( ) or Spurs, is an English football club located in Tottenham, Haringey, London, that competes in the Premier League. Answer: Tottenham Hotspur Football Club\nSolution:" }, { "from": "gpt", "value": "What football club, known a Spurs, featured English player Paul Miller?" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Generate an explanation for the given claim using the provided supporting material from the paragraph. Please consider the following points while generating an output. 1) The claim will always have supporting proof in the paragraph, and the paragraph will have a clear point of view supporting the claim. 2) There can be instances where direct correlation to the claim is not available. Make use of the sentences in the paragraph to provide a corresponding output supporting the claim. 3) The explanation should be at least one and at most twelve sentences long.\n\nLet me give you an example: Paragraph: \"Although the story didn’t cite the cost of appendectomy – emergency or urgent surgery – and we wish it had, we nonetheless will give it a satisfactory score because it at least cited what the editorial writer wrote, \"\"A secondary benefit is the savings to the hospital generated by minimizing staff and anesthesiologist presence late in the evening and during the wee hours of the morning.\"\" As with our harms score above, although the story didn’t give absolute numbers, in this case we think it was sufficient for it to report that \"\"The scientists found no significant difference among the groups in the patients’ condition 30 days after surgery or in the length of their operation or hospital stay.\"\" Although the story didn’t give absolute numbers, in this case we think it was sufficient for it to report that \"\"The scientists found no significant difference among the groups in the patients’ condition 30 days after surgery or in the length of their operation or hospital stay.\"\" Despite running less than 300 words, this story did an adequate job in explaining the quality of the evidence, including pointing out limitations. No disease-mongering here. The story meets the bare minimum requirement for this criterion in that it at least cited what an editorial stated. The focus of the story was on a study comparing emergency appendectomy with surgery done up to 12 hours later or beyond. This is the whole focus of the story – and one we applaud – when it begins:  \"\"Appendectomy is the most common emergency surgery in the world, but it doesn’t have to be.\"\" There were no claims made about the novelty of this research, and we may have wished for a bit more context on this. Nonetheless, the potential for guiding future care decisions was made clear. Not applicable. Given that the story only pulled excerpts from the journal article and the accompanying editorial, and didn’t include any fresh quotes from interviews, we can’t be sure of the extent to which it may have been influenced by a news release.\". Claim: Some appendicitis cases may not require ’emergency’ surgery\nThe answer to this example can be: We really don’t understand why only a handful of mainstream news organizations reported this story. (At least in what we found.) The most common emergency surgery in the world. Rushing to emergency surgery may not carry any benefit. Waiting a few hours may be safer and less expensive. Why is that not a story? We applaud USA Today for finding time and space – and clearly it didn’t need to free up much space to do a good job telling the story. The story explains that as many as 300,0 appendectomies are done each year in the US. That figure alone explains why this is an important study to report.\nHere is why: The output is an analysis of the claim while considering the paragraph as a reference. The output highlights the key features presented in the paragraph and explains the claim accordingly.\n\nOK. solve this:\nParagraph: Scientists analyzed more than 10,000 wastewater injection wells where 96 billion gallons of fluid — leftover from hydraulic fracturing — are pumped yearly. The amount of wastewater injected and the depth are key to understanding the quake outbreak since 2009, they reported in Thursday’s journal Science . The quakes included a damaging magnitude 5.8 in 2016, the strongest in state history. State regulators could cut about in half the number of man-made quakes by restricting deep injections in the ground, said lead author Thea Hincks, an earth scientist at the University of Bristol in the United Kingdom. Companies drilling for oil and gas should not inject waste within 600 to 1500 feet (200 to 500 meters) of the geologic basement. That’s the stable harder rock deep underground usually made of metamorphic and igneous rocks. That region is usually crisscrossed with earthquake faults. The closer you get to the faults, the more likely you are to trigger them, said Stanford University geophysicist Matthew Weingarten, who wasn’t part of the study. Lab experiments show basement rocks are more susceptible to earthquakes because “having fluids in a rock is going to weaken the rock,” said co-author Thomas Gernon, a geologist at the University of Southampton. Previous studies had pinpointed the amount of fluids injected into wells as an issue. Gernon said volume does trigger earthquakes, but when volume levels were reduced the number of quakes didn’t drop as much as had been expected. That’s because where the stuff is put matters slightly more, he said. The findings only apply to quakes in Oklahoma, researchers said. ___ Follow Seth Borenstein on Twitter at @borenbears . His work can be found here . Claim: Oklahoma quakes tied to how deep wastewater is injected.\nAnswer:" }, { "from": "gpt", "value": "A new study finds that a major trigger of man-made earthquakes rattling Oklahoma is how deep — not just how much — fracking wastewater is injected into the ground." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given a sentence in Japanese. Your job is to translate the Japanese sentence into English.\n\n第一にキリバス共和国が彼ら自身の利益になると理解したからです\nSolution: And it was primarily because Kiribati realized that this was in their own self-interest to do this.\nWhy? The Japanese sentence is correctly translated into English, because the meaning is preserved.\n\nNew input: しかし十分に近いでしょう自然も完璧ではないですから\nSolution:" }, { "from": "gpt", "value": "But it should be be perfect enough, because nature doesn't do perfect either." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given a sentence in English, and your task is to translate it into Persian.\nOne example: I heard enough of what she said to you last night to understand her unwillingness to be acting with a stranger;\nSolution is here: دیشب شنیدم به تو چه می‌گفت. فهمیدم که دوست ندارد با یک غریبه این نقش را بازی کند.\nExplanation: This is a good example. The above sentence is correctly translated from English to Persian.\n\nNow, solve this: before either Fanny or the steady old coachman, who always attended her when she rode without her cousins, were ready to set forward.\nSolution:" }, { "from": "gpt", "value": "طوری که هنوز نه فانی آماده شده بود و نه درشکه چی پیر منضبطی که در غیاب خاله‌زاده‌های فانی هنگام سواری همراهی‌اش می‌کرد." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "A text is given in Gujarati. Translate it from the Gujarati language to the Malayalam language. The translation must not omit or add information to the original sentence.\n\nપ્રધાનમંત્રીએ કેરળની મુલાકાત લીધી, રાહત અને બચાવ કામગીરીની સમીક્ષા કરી" }, { "from": "gpt", "value": "രക്ഷാപ്രവര്‍ത്തനവും ദുരിതാശ്വാസ പ്രവര്‍ത്തനവും വിലയിരുത്തി" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: Combine the given two facts to write a concluding fact. Note that there should be some parts of the first and second facts that are not mentioned in this conclusion fact. Your combined fact should be the result of a chain between the two facts. Chains form when two facts connect together to produce a concluding fact. An example of a chain is: \"pesticides cause pollution\" (fact1) + \"pollution can harm animals\" (fact2) → \"pesticides can harm animals\" (conclusion fact). Parts of the concluding fact overlap with the first and the second fact. To construct such a concluding fact, a useful way is to borrow the subject from one fact and the ending conclusions from another fact.\nProblem:Fact 1: Soil can be depleted of nutrients. \nFact 2: For the nonrenewable resources, depletion means extraction of the available natural resources.\nSolution:" }, { "from": "gpt", "value": "soil nutrition can be extracted." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Definition: In this task you are given a small conversation between two persons and 4 options on how the conversation should continue. Your job is to choose the most reasonable option. The conversation and the options are separated by a newline character. Each dialogue in the conversation are separated by a comma. F and M indicate female and male, respectively.\nInput: M: Oh, it's already 10:30 now. I haven't finished my homework yet. ,F: Don't worry. The clock on the wall is 20 minutes fast.\n(A) M: So it is 10:10 now. (B) M: So it is 10:00 now and I have already finished my homework. (C) M: So it is 10:10 now and I am so lucky because I have already finished my homework. (D) M: I’m sorry, I didn’t understand. Could you repeat a little louder, please?\nOutput:" }, { "from": "gpt", "value": "A" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a statement written in Assamese. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\n\nInput: Consider Input: Statement: জম্মু আৰু কাশ্মীৰ তিনিটা মূল অংশৰে গঠিত: জম্মু, কাশ্মীৰ উপত্যকা আৰু <MASK>। গ্ৰীষ্মকালত ৰাজ্যখনৰ ৰাজধানী শ্ৰীনগৰ আৰু শীতকালত ৰাজধানী কাশ্মীৰ। কাশ্মীৰ উপত্যকা ইয়াৰ পৰ্বতমালা আৰু প্ৰাকৃতিক সৌন্দৰ্য আৰু ইয়াত থকা পবিত্ৰ তীৰ্থস্থান সমূহৰ বাবে বিখ্যাত। প্ৰতি বছৰে হাজাৰ হাজাৰ হিন্দু তীৰ্থ যাত্ৰী এই তীৰ্থসমূহ দৰ্শনৰ বাবে কাশ্মীৰলৈ আহে। পৰ্বতৰ নৈসৰ্গিক সৌন্দৰ্য আৰু বৌদ্ধ ধৰ্মীয় সংস্কৃতিৰ বাবে বিখ্যাত লাডাখক \"লিটল (সুক্ষ্ম) তিব্বত\" বুলিও জনা যায়। জম্মু আৰু কাশ্মীৰ ভাৰতৰ একমাত্ৰ মুছলিম সংখ্যাগৰিষ্ঠ ৰাজ্য।\n\n Option A: ভাৰত\n\n Option B: পাঞ্জাব\n\n Option C: ভাৰতে\n\n Option D: লাডাখ\n\nOutput: লাডাখ\n\n\nInput: Consider Input: Statement: ইং ১৮৪২ চনত বৃটিছে শদিয়া আৰু মটক ৰাজ্য নিজ দখললৈ অনাৰ পিছত জিলাৰ আকাৰ বৃহৎ হোৱাত আৰু লক্ষীমপুৰৰ আওহতীয়া অৱস্থিতি, যাতায়তৰ অসুবিধাৰ বাবে জিলাৰ সদৰ দক্ষিণপাৰৰ <MASK> চহৰলৈ স্থানান্তৰিত কৰিলে আৰু উত্তৰ পাৰৰ ভূখণ্ডক এটা মহকুমা কৰি নাম থলে উত্তৰ লক্ষীমপুৰ। ইং ১৯৭১ চনৰ ২ অক্টোবৰ গান্ধী জয়ন্তীৰ দিনা সেই সময়ৰ অসমৰ মুখ্যমন্ত্ৰী প্ৰয়াত মহেন্দ্ৰ মোহন চৌধুৰীৰ আদেশ মৰ্মে লক্ষীমপুৰ জিলাক দ্বি-খণ্ডিত কৰি ডিব্ৰুগড় জিলা আৰু লক্ষীমপুৰ জিলা গঠন কৰে। উত্তৰ লক্ষীমপুৰক নব গঠিত লক্ষীমপুৰ জিলাৰ সদৰ ঘোষণা কৰে।\n\n Option A: ডিব্ৰুগড়\n\n Option B: হিমালয়\n\n Option C: বিহপুৰীয়া\n\n Option D: নাৰায়ণপুৰ\n\nOutput: ডিব্ৰুগড়\n\n\nInput: Consider Input: Statement: ভাস্কৰাব্দ ভাৰতৰ <MASK> ৰাজ্যত প্ৰচলিত এক প্ৰকাৰৰ সৌৰ বৰ্ষপঞ্জী। শকাব্দ, বিক্ৰম সংবৎ আদিৰ লগত মিল থাকিলেও ভাৰতৰ বাঙালী সম্প্ৰদায়ৰ মাজত প্ৰচলিত আৰু বাংলাদেশৰ জাতীয় বৰ্ষপঞ্জী বংগাব্দৰ লগত ভাস্কৰাব্দৰ বিশেষ সাদৃশ্য আছে। প্ৰাচীন কামৰূপৰ বৰ্মণ ৰাজবংশৰ শ্ৰেষ্ঠ ৰজা কুমাৰ ভাস্কৰ বৰ্মাৰ ৰাজ অভিশেষৰ পৰা এই বছৰ গণনা হয়৷ খ্ৰীষ্টান বছৰৰ তুলনাত ই ৫৯৩ বছৰ পাছ পৰা৷ অৰ্থাৎ খ্ৰীষ্টাব্দৰ পৰা ৫৯৩ বছৰ বিয়োগ কৰিলে চলিত ভাস্কৰাব্দটো পোৱা যায়।\n\n Option A: বিহাৰ\n\n Option B: বাংলাদেশ\n\n Option C: অসম\n\n Option D: শালস্তম্ভ\n\n" }, { "from": "gpt", "value": "Output: অসম\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given a sentence in Arabic, generate a new Arabic sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\nEx Input:\nإن تطوير تكنولوجيا المعلومات سيؤدي إلى ثورة الأعمال التجارية.\n\nEx Output:\nومن شأن تطوير تكنولوجيا التهيئة أن يُحدث ثورة في مجال الأعمال التجارية.\n\n\nEx Input:\nيمكنك استخدام مُقدم مطعم لتعتمد عليه.\n\nEx Output:\nيمكنك استخدام طاوله لأكلها\n\n\nEx Input:\nاللسان يمكن أن يساعد في فن التقبيل.\n\nEx Output:\n" }, { "from": "gpt", "value": "« ثعلب » بدل من المبتدأ « يملؤه التقبيل » أي القبل.\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher: In this task, you are given a sentence in the Hindi language and a corresponding English translation of the Hindi sentence. Your task is to generate a label \"Yes\" if the translation is correct, otherwise generate label \"No\". In the translation, English sentence should preserve the number as it is and it should be in sentence case (capitalize only the first word of each sentence and noun).\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nHindi: पहले दो को अविश्वसनीय मानकर बाकी पांच मुखबिरों के आधार पर मुकदमा चलाया गया| \n English: The first two were found unreliable and the prosecution case rested mainly on the evidence of the remaining five approvers .\nSolution: Yes\nReason: Hindi sentence is properly converted into English sentence because the Hindi sentence also says that the first two were judged to be untrustworthy, thus the prosecution relied heavily on the testimony of the remaining five approvers. Also, the translated sentence is in a sentence case.\n\nNow, solve this instance: Hindi: बहुत बड़ी क्रांति को जन्म देता है। \n English: Evaluation - Woman's (Receiver)convenience.... Woman's (Receiver)troubles.... Woman's (Receiver)pleasure\nStudent:" }, { "from": "gpt", "value": "No" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given a sentence in French, generate a new French sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\n[EX Q]: Vous pouvez taper de l'argent dans une banque pour lui faire confiance.\n[EX A]: Vous pouvez mettre de l'argent dans une banque pour la jouer.\n\n[EX Q]: Si yuo sont inspirés par une certaine expérience, vous pourriez écrire un poème à ce sujet.\n[EX A]: Si yuo sont transformés par une certaine expérience, vous pourriez écrire un poème à ce sujet.\n\n[EX Q]: Vous trouverez probablement un piano droit dans un magasin de musique.\n[EX A]:" }, { "from": "gpt", "value": "Vous êtes susceptible de lire un piano droit dans un magasin de musique.\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task, you are given a sentence in the english language. Here, your job is to convert english sentence into the bulgarian language.\nTeacher: Now, understand the problem? Solve this instance: Agenda of the next sitting: see Minutes\nStudent:" }, { "from": "gpt", "value": "Дневен ред на следващото заседание: вж. протокола" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.\n\nEx Input:\nIn a pot, combine salt, sugar, vinegar and oil. Bring to just a boil, stirring to dissolve sugar and salt. Add onions and return to a boil., Using a slotted spoon, pack onions into canning jars. Pour in pickling liquid to cover. Seal jars with lids and refrigerate for at least 3 days to blend flavors. Store in the refrigerator for up to 1 month.\n\nEx Output:\nsalt, sugar, white wine vinegar, corn oil, white pearl onions\n\n\nEx Input:\nMix together and heat to boiling., Pour over item to be barbecued.\n\nEx Output:\nonion, tomato ketchup, water, vinegar, Worcestershire sauce, salt, paprika, chili powder, pepper, cinnamon, ground cloves\n\n\nEx Input:\nHeat oven to 350°., Brown meat and drain., Add green pepper and onion., Cook until tender., Stir in tomatoes, tomato sauce, water and seasonings., In a 2-quart casserole dish, layer half the noodles, half the meat sauce and half the Velveeta cheese., Repeat layers., Sprinkle with Parmesan cheese., Bake 30 minutes.\n\nEx Output:\n" }, { "from": "gpt", "value": "ground beef, onion, green pepper, tomatoes, tomato sauce, water, bay leaf, salt, black pepper, mostaccioli, Velveeta cheese, Parmesan cheese\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head happens after the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.\n\nHead: PersonX takes PersonY to get<sep>Tail: PersonX picks up PersonY in their car\nOutput:" }, { "from": "gpt", "value": "Yes" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task, you are given a sentence from the Quran in English, and your task is to translate it into Persian.\nTeacher: Now, understand the problem? Solve this instance: (Man) will have no power, and no helper.\nStudent:" }, { "from": "gpt", "value": "پس انسان را [در آن روز در برابر عذاب] نه نیرویی است و نه یاوری." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou will be given a passage consisting of set of facts and a question as input. The task is to answer a question of form 'Where is <person_name>?' using one of the given facts to determine the latest location of the person. Answer should be a word/phrase describing the location from the supporting fact. Avoid answers that are incomplete or incorrect.\n\nPassage: John went back to the hallway. Daniel journeyed to the bedroom. Question: Where is John?\nOutput:" }, { "from": "gpt", "value": "hallway" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a context, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both context and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the context or linked information.\nProblem:Context: Chosen to be first President of Colombia, was General Link Information: The following day, Congress elected Francisco Antonio Zea Díaz, first Vice President of Colombia. Answer: Francisco Antonio Zea\n\nJuan\nSolution:" }, { "from": "gpt", "value": "Between the first president and the first vice president of Colombia, who was older?" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a question. You have to answer the question based on your information.\nExample: Roman Yakub won first price in a Choral Composition Competition at a liberal arts college founded by who?\nOutput: William Egbert\nThis is a good example, and output correctly answers the question.\n\nNew input case for you: Juan de Cáceres y Ulloa was an organist of this cathedral, which is the main catholic church in which city?\nOutput:" }, { "from": "gpt", "value": "Buenos Aires, Argentina" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you will be presented with a question having multiple possible answers in Vietnamese language. And you should choose a most suitable option out of \"A\", \"B\", \"C\", \"D\", and \"E\" based on your commonsense knowledge.\n\nQuestion: Bạn có thể làm gì để chia sẻ những kỷ niệm của bạn khi đến thăm viện bảo tàng? \n Options: A chụp ảnh B khóc C nói to D thì thầm E sự giải trí \n" }, { "from": "gpt", "value": "A" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: In this task, you are given a sentence in the English language and your task is to convert it into the Swedish language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).\nInput: So there was not much sympathy for this budget line when it was abolished.\nOutput:" }, { "from": "gpt", "value": "Så det var inte många som sörjde att denna budgetpost avskaffades." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given a context and four options. Each option is a suggested ending for the context. You should read the context and pick the best ending for the context. Please answer with \"A\", \"B\", \"C\", and \"D\". \nOne example is below.\nQ: [header] How to create a christmas tree forest [title] Consider the type of tree you want to plant. [step] There are a wide variety of christmas trees and include fir, pine, spruce, cypress, and cedar. These trees thrive in different climates and look different from one another. <sep> (A) It is important to research the tree before setting up your tree to try it out to make sure you can write the tree's growing season so that you can get the most supplies you need. If you're just interested in having a tree stand out, then make sure to check for the following : [substeps] Spruce trees. (B) [substeps] Trees green may be used in a mix of green and evergreen. Greens, such as pintos and olive oil, may be more delicate than these. (C) Where the trees grow together is up to you. [substeps] Spruce trees light up the night for hours in the morning and drown out the morning sunrise between afternoons. (D) Think about where your tree forest will be located and choose a tree that can thrive in that climate. [substeps] Balsam firs are a popular christmas tree species that grow in the northern united states and canada, in hardiness zones 3-5 or states like minnesota, north dakota, and montana.\nA: D\nRationale: This is a good example. Only option D is about Christmas trees. So, it's the correct option.\nQ: [header] How to choose an intellectual property lawyer [title] Identify your type of intellectual property. [step] There are several types. Although some lawyers will handle legal issues involving all types, some lawyer will specialize in one or two. <sep> (A) [substeps] The strength of your intellectual property law may influence the clientele. For example, a powerful attorney might be willing to resolve a complex dispute with your potential client. (B) You should identify which type of intellectual property you have : [substeps] Patents. Patents are granted by the federal government and confer the right to make, use, sell, or import a product exclusively for a limited amount of time. (C) [substeps] Each type forms a phrase with an emphasis on one or another. You often ask prospective lawyers what type of intellectual property they will represent you. (D) These may include : [substeps] Intellectual property intellectual property legal liability intellectual property [title] Search online for a lawyer specializing in intellectual property. [step] Both are free and easy to find.\nA:" }, { "from": "gpt", "value": "B" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:Translation from English to Telugu.\nTeacher: Now, understand the problem? Solve this instance: We're friends in need and friends indeed\nStudent:" }, { "from": "gpt", "value": "మేమునిజానికిఅవసరం మరియు స్నేహితులతో స్నేహితులు" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given a sentence in either Spanish or English. Your task is to determine the language of the input sentence. Input sentences can only be in Spanish or English, and they cannot be in two languages ​​at the same time.\nExample: All of us here are pleased that the courts have acquitted him and made it clear that in Russia, too, access to environmental information is a constitutional right.\nExample solution: English\nExample explanation: Input sentence is in English language.\n\nProblem: El debate anual sobre estos temas marca la pauta para el rumbo general que ha de seguir la organización política de la Unión Europea.\n" }, { "from": "gpt", "value": "Solution: Spanish" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: A text is given in Hindi. Translate it from the Hindi language to the Marathi language. The translation must not omit or add information to the original sentence.\nInput: लोकांनी समाज माध्यमांच्या व्दारे, ‘माय गव्ह’ आणि ‘नरेंद्र मोदी अॅप’ वर खूप मोठ्या संख्येनं अतिशय सकारात्मक प्रतिसाद दिला आणि आपले अनुभव ‘शेअर’ केले आहेत.\nOutput:" }, { "from": "gpt", "value": "मुझे बहुत ख़ुशी हुई कि भारी संख्या में लोगों ने social media platorm, MyGov और NarendraModi App पर बहुत ही positive response दिया, अपने अनुभव share किये।" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Definition: In this task, you are given a sentence from the Bible in English, and your task is to translate it into Persian.\nInput: And king Arad the Canaanite, which dwelt in the south in the land of Canaan, heard of the coming of the children of Israel.\nOutput:" }, { "from": "gpt", "value": "و از عییم کوچ کرده، در دیبون جاد فرود آمدند." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head happens after the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.\n\nQ: Head: PersonX activates a shadow over everyone<sep>Tail: controlling\n\nA: No\n****\nQ: Head: PersonX avenges PersonY's death<sep>Tail: PersonX pulls out a knife\n\nA: Yes\n****\nQ: Head: PersonX takes the red pill<sep>Tail: PersonX groans in pain\n\nA:" }, { "from": "gpt", "value": "Yes\n****\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Definition: A text is given in Oriya. Translate it from the Oriya language to the Tamil language. The translation must not omit or add information to the original sentence.\nInput: ଏହି ଅବସରରେ ଏକ ସମାବେଶକୁ ସମ୍ବୋଧିତ କରି ପ୍ରଧାନମନ୍ତ୍ରୀ ସ୍ମରଣ କରି କହିଥିଲେ ଯେ, ବିଗତ ଚାରି ବର୍ଷରେ ବିଭିନ୍ନ ସମୟରେ ସେ ଜାମ୍ମୁ-କାଶ୍ମୀର ରାଜ୍ୟ ଗସ୍ତ କରିଛନ୍ତି ।\nOutput:" }, { "from": "gpt", "value": "ஜம்மு-காஷ்மீர் காவல்துறையை வலுப்படுத்த இந்திய ஆயுதக் காவல்படையின் ஐந்து பட்டாலியன்கள் அனுப்பப்பட்டு உள்ளன." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task you are given an anecdote. You must find out whether the anecdote is something the author has done or is considering doing. Label the instances as \"HISTORICAL\" when the author has already done something and label them as \"HYPOTHETICAL\" when the author is considering doing something in the future.\nTeacher: Now, understand the problem? Solve this instance: This past Friday, I had a party at my house. I invited a few friends and coworkers over for some drinks, games and food. One particular guest was sort of a plus one, but not really. He was the friend of a coworker that had invited him along, but they came to the party separately. I thought it was no big deal, we had plenty of food and drinks to go around.\n\nIt was about 20 minutes in when I noticed this guy standing around awkwardly. So I asked if everything was alright, and he said yes. He said that no one was talking to him. So I talked with him for a moment, learned more about him. Then, I introduced him to a friend of mine who had similar interests. They chatted for a bit, but 5 minutes later, I saw him standing alone again. I asked what’s up, and he said no one was talking to him.\n\nI asked where my friend was, and he just shrugged. I suggested that he join a game of uno going on, but he refused. I suggested he mingle, and he also refused.\n\nNow this is where I started to get annoyed. He says no one is talking to him, despite the fact that he was being talked to earlier. And he says no one is talking to him, when he can go up to someone and say “Hi”. At this point, I’m starting to see what’s going on; he just wants to feel sorry for himself, or he wants everyone else to drop what they’re doing and make him feel less awkward. So I told him that if he’s just going to stand around, he can leave. He did, and I let his friend (my coworker) know. She said it was shitty to tell him to leave, but I explained that he wasn’t making the effort to socialize with others, and I didn’t have time to drag him around to make him talk to people. AITA for this?\n\nStudent:" }, { "from": "gpt", "value": "HISTORICAL" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "The input contains a debate topic, an argument on the topic and a keypoint, separated by \"<sep>\". Your task is to answer if the keypoint matches the argument and summarizes exactly what the argument means, in the context of the given topic.\n\nTopic: Assisted suicide should be a criminal offence<sep>Argument: Terminally ill patients who just don't want to continue suffering have a valid reason to contemplate suicide, and someone who wants to help ease their pain should not be punished.<sep>Keypoint: Assisted suicide gives dignity to the person that wants to commit it\nFalse\n\nTopic: The vow of celibacy should be abandoned<sep>Argument: Vow of celibacy is important for some religious members and should be allowed to remain.<sep>Keypoint: Celibacy is a strong religious belief\nTrue\n\nTopic: We should legalize prostitution<sep>Argument: Legalization of prostitution would allow regulation and provide safe environments<sep>Keypoint: Legalizing sex work increases sex workers' benefits (e.g. health care, safe sex, unionization, etc.)\n" }, { "from": "gpt", "value": "False\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: This task is to translate the English language Input to Telugu Language Output\nSee one example below:\nProblem: I am very happy\nSolution: స్నేను చాలా సంతోషంగా ఉన్నాను\nExplanation: The translation is correct with meaning of the sentence not being impacted.\n\nProblem: For more information on our product and services please contact us at:\nSolution:" }, { "from": "gpt", "value": "మా ఉత్పత్తులు మరియు సేవల గురించి మరింత సమాచారం కోసం దయచేసి మమ్మల్ని ఈ చిరునామలో సంప్రదించండి:" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Italian. Your job is to translate the Italian sentence into Galician.\nProblem:Ebbene, si può avere meno controllo, o un tipo diverso di controllo?\nSolution:" }, { "from": "gpt", "value": "Ben, podes facelo con menos control, ou cun control diferente?" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\nPROBLEM: Comment: In 1988, two young American men beat to death Mulugeta Seraw, an Ethiopian graduate student. Mulugeta’s only crime, according to them, was his skin color. \n\nAs it turned out, these men were members of the White Aryan Resistance (WAR), a white supremacist group founded by neo-Nazi and KKK grand dragon, Tom Metzger. \n\nMetzger began his racist career in 1979 by patrolling the U.S./Mexican border in San Diego as a private citizen stating he was concerned about illegal immigration. \n\nWhen he began hosting a television show aimed at white nationalism, his anti-immigrant stance quickly became an anti-anything not white, Christian and male. Additionally, he sponsored a rock concert for Aryan youth which is how the Seraw killers were introduced to his racist gutter spewed antics.\n\nThe Southern Poverty Law Center sued Metzger using the vicarious liability concept and won.\n\nSOLUTION: Non-obscene\n\nPROBLEM: Comment: fucking people make me sick!!! throw your ass out of a car!\n\nSOLUTION: Obscene\n\nPROBLEM: Comment: Oh, I agree, but I was commenting on the horrible idea of Sarah Palin as Sec. of the Interior. She'll be out shooting the fricking buffalo!\n\nSOLUTION:" }, { "from": "gpt", "value": "Obscene\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given a post in English from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer \"hateful\" or \"Non-hateful\". Note that the URLs in the text have been replaced with [Link].\n\nEx Input:\nPost: can you like choke me once and for all??\n\nEx Output:\nNon-hateful\n\n\nEx Input:\nPost: #EU offers states funding to take in migrants [Link]\n\nEx Output:\nNon-hateful\n\n\nEx Input:\nPost: @TheShaggyMarlin Ive told this story many a time: first time I heard 'cunt' used against a woman was in 'One Flew O… [Link]\n\nEx Output:\n" }, { "from": "gpt", "value": "Non-hateful\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: In this task, your goal is to judge a correct answer to a given question based on an associated paragraph and decide if it is a good correct answer or not. A good correct answer is one that correctly and completely answers the question. A bad correct answer addresses the question only partially or incorrectly. If you think the given correct answer is good, indicate it by responding \"Yes\". Otherwise, respond \"No\". There are only two types of responses possible: \"Yes\" and \"No\".\nInput: Paragraph- Sent 1: In 1989 , Kevin Flynn , software engineer and the CEO of ENCOM International , disappears .\nSent 2: Twenty years later , his son , Sam , now ENCOM 's primary shareholder , takes little interest in the company beyond playing an annual trick on the board of directors ; but is requested by his father 's friend , ENCOM executive Alan Bradley , to investigate a message originating from Flynn 's shuttered Video arcade .\nSent 3: There , Sam discovers a hidden basement in which Sam unintentionally teleports himself to the Grid , a virtual reality created by his father .\nSent 4: On the Grid , Sam is sent to compete against a masked program called Rinzler who , having realized that Sam is a human User after seeing him bleed , takes him before CLU , an alter ego of Kevin Flynn who rules the Grid .\nSent 5: CLU nearly kills Sam in a Light Cycle match ; but the latter is rescued by Quorra , an `` apprentice '' of Flynn 's , who conveys him to his father outside CLU 's territory .\nSent 6: There , Flynn reveals to Sam that he had been working to create a `` perfect '' computer system and had appointed CLU and Tron its co-creators .\nSent 7: During this construction , the trio discover a species of naturally-occurring `` isomorphic algorithms '' , not conceived by Flynn , bearing the potential to resolve various mysteries in science , religion , and medicine .\nSent 8: CLU , having deemed them an aberration , betrayed Flynn , captured Tron , and destroyed the ISOs .\nSent 9: Meanwhile , the `` I\\/O portal '' permitting travel between the two worlds had closed , leaving Flynn captive . \nQuestion: After CLU nearly kills Sam, CLU and Tron are revealed to be the co-creators of what technological ideal? \nCorrect Answer: computer systems.\nOutput:" }, { "from": "gpt", "value": "No." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No.\n\nExample Input: Question: What was the population of Spoleto the first year that Raffaello de Banfield was Director of the (\"Festival of the two worlds\")? Passage:Raffaello de Banfield attended the Swiss International \"Lyceum Alpinum Zuoz\", the \"Dante Alighieri\" Lyceum in Trieste, the University of Bologna and the Benedetto Marcello Conservatory in Venice led by Gian Francesco Malipiero. He studied composition from 1946 to 1949 at the National Conservatory (under the direction of Henri Busser) with Nadia Boulanger in Paris. In these years he met Herbert von Karajan with whom he had a lifelong friendship, and also with artists such as Pablo Picasso, Jean Cocteau and Francis Poulenc. In the United States he belonged to the intellectual circle surrounding the writer and composer Paul Bowles, through which he met Tennessee Williams and Leonard Bernstein. In 1949 through the painter Leonor Fini he was introduced to the choreographer and ballet dancer Roland Petit; out of this grew the ballet Le combat (\"The Duel\"), which had its first original production in London in 1949. This piece, based upon the Tancred and Clorinda episode in Torquato Tasso's poem Gerusalemme liberata, was performed 39 times at the Vienna State Opera in the choreography of Dimitrije Parlic between 1959 and 1973. Until 1958 he spent time between Paris and New York and maintained a friendship also with Maria Callas. After years abroad in Italy, France, England and the United States, where he lived for more than ten years, he was from 1972 to 1996 Director of the Giuseppe Verdi Theatre in Trieste and he comprehensively renovated and modernised the Opera House. From 1978 to 1986 he was Director of the \"\" (\"Festival of the two worlds\") in Spoleto, Italy.\n\nExample Output: a\n\nExample Input: Question: Did Sætren study at multiple institutions within the same country between 1862 and 1865? Passage:Sætren studied at Lillehammer Latin- og Realskole, at Qvams skole in Christiania and at the Swiss Federal Institute of Technology Zurich from 1862 to 1865. In 1866 he started working as a draftsman for Kanalvæsenet, the body for exploitation of Norwegian water resources, and held various positions at Kanalvæsenet over a period of 41 years. He ended his career as manager for the Bandak-Norsjø Canal from 1891 to 1907. The boat locks of the Bandak-Norsjø Canal could lift boats with a length of up to 100 feet. The canal became an important water transport system, and also a tourist destination. Sætren was a counsellor for industrialist Sam Eyde, the founder and first mangager of Norsk Hydro, who acquired rights for exploiting waterfalls for hydroelectric power. Sætren published maps and overviews of water resources in Norway, such as his map from 1904. He was the first editor of the magazine Norsk Teknisk Tidsskrift, which he edited from 1883 to 1886. He was also a proponent for the construction of the Holmenkoll Line, and chaired the board of directors for ten years from 1896. He was decorated Knight of the Royal Norwegian Order of St. Olav in 1893.\n\nExample Output: b\n\nExample Input: Question: When was the spaceship which attached to the mother ship created? Passage:Baxter publicly credits his fascination with the space program to reading From the Earth to the Moon by Jules Verne as a young boy. Baxter holds the distinction of First Founder of Virgin Galactic, a space tourism company announced by Sir Richard Branson on September 25, 2004. Baxter purchased the first commercial space flight ticket at $200,000 USD after viewing a 60 Minutes segment featuring Burt Rutan, winner of the $10,000,000 X Prize for the first non-governmental organization to launch a reusable manned spacecraft into space twice within two weeks, and thereafter, earning him the nickname \"Rocket Man\". Rutan is also the designer of Sir Richard Branson's SpaceShipTwo, which attached to the mother ship, will be carried to about 16 kilometers or 52,000 feet by a carrier aircraft, White Knight Two. At that point, when the carrier aircraft reaches its maximum height, the SpaceShipTwo vehicle will separate and continue to over 100 km (the Kármán line, a common definition of where \"space\" begins). Despite the crash of the first iteration of SpaceShipTwo during a test flight on October 31, 2014, Baxter remains optimistic about his upcoming flight and continues to hold his place at the top of the passenger list to become the world's first commercial space tourist.\n\nExample Output:" }, { "from": "gpt", "value": "b\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: insult and non-insult. Insult is any lanugage or act that is disrespectful or scornfully abusive.\nPROBLEM: Comment: D's won the popular vote in 20 of the 50 states. No, we are not in the minority, well maybe in California\n\nSOLUTION: Non-insult\n\nPROBLEM: Comment: Ok Mark, it's time for you to resurface your guff now there's a break in our colder than usual winter. Too bad for your pitch that Dr John Bates, a top NOAA scientist with an impeccable reputation has revealed that NOAA falsified data before the Paris accord. Quick team, muzzle that scientist!\n\nSOLUTION: Non-insult\n\nPROBLEM: Comment: Palin is an idiot, in the same mold as Trump. #losers\n\nSOLUTION:" }, { "from": "gpt", "value": "Insult\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Italian.\n\nExample Input: מייק שאל אותי שאלה היפותטית:\nExample Output: Mike mi fece una domanda ipotetica.\n\nExample Input: אבל באמצעות צורה כזו של הדגמה מוחשית, סריגה, צורות אחרות של מלאכת-יד פלסטית, אנשים יכולים להיות מעורבים בדברים הכי מופשטים, ברעיונות תאורטיים, בעלי עוצמה — רעיונות מהסוג שבדרך-כלל צריך ללכת בשבילם לאוניברסיטה וללמוד מתמטיקה גבוהה, מקום בו אני למדתי לראשונה על מרחב היפרבולי.\nExample Output: Ma attraverso questo tipo di modalità, il lavoro all'uncinetto o altre forme di gioco plastico-creativo, le persone possono venire catturate dalle più astratte, potenti idee teoriche; Quei tipi di concetti per i quali, di solito, devi andare all'università per studiarli al corso di matematica superiore, dove, per la prima volta, ho studiato lo spazio iperbolico.\n\nExample Input: אברקדברה.\nExample Output:" }, { "from": "gpt", "value": "Abracadabra.\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Q: You are given a sentence in Persian. Your job is to translate the Farsi sentence into English.\nخود انشتین بیشتر ادامه زندگی خود را در جستجوی بیهوده برای یک نظریه وحدت در فیزیک صرف کرد ، و فیزیکدان ‌ ها این را از آن پس ادامه داد ‌ ه ‌ اند.\nA:" }, { "from": "gpt", "value": "Einstein himself spent most of his later years on a futile search for a unified theory of physics, and physicists have kept at it ever since." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Q: You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Portugese.\nאז נהייתי מעורב בג 'יהאד אלים באמצע שנות ה-80, כשאני מתחיל באפגניסטן.\nA:" }, { "from": "gpt", "value": "Portanto, envolvera-me na Jiade violenta em meados dos anos 80, começando pelo Afeganistão" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Teacher:In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: religious or non-political religious on the topic.\nTeacher: Now, understand the problem? Solve this instance: খা খা খা আমায় চুষে চুষে খা আমায় গিলে খা\nStudent:" }, { "from": "gpt", "value": "non-religious" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "This task involves creating questions from a given passage that involve some kind of complex reasoning (including numerical reasoning). \nThe generated questions must require looking at more than one part of the passage to answer. Try to use a variety of reasoning types in your questions (some of the sample reasoning types are illustrated in the 'positive examples' field) and also have a variety of answer types (spans, numbers, dates). A span is a continuous phrase taken directly from the passage or question. In such questions, the answer spans are recommended to be five words. Questions with answer type \"number\", are expected to start with \"How many\". For instance, \"How long did an event last?\" can be phrased as \"How many years did an event last?\". To increase diversity, try to create more questions for which the answer will be multiple spans. Please create questions that require AT LEAST 2 arithmetic operations as illustrated in the 'positive examples' field. You are encouraged to try DIFFERENT COMBINATIONS of operations and not just limit to the combinations shown in those examples. The more challenging questions you create, the better it is.\n\n[EX Q]: Passage: Coming off their home win over the Bengals, the Texans flew to the Hubert H. Humphrey Metrodome for a Week 9 interconference duel with the Minnesota Vikings. In the first quarter, Houston trailed early as Vikings RB Adrian Peterson got a 1-yard TD run. The Texans responded with CB Jacques Reeves returning an interception 44 yards for a touchdown. In the second quarter, Minnesota answered with QB Gus Frerotte completing an 8-yard TD pass to WR Sidney Rice and a 49-yard TD pass to WR Bernard Berrian. In the third quarter, Houston tried to rally as QB Sage Rosenfels completed a 3-yard TD pass to WR David Anderson. In the fourth quarter, the Vikings replied with Frerotte completing a 25-yard TD pass to TE Visanthe Shiancoe. The Texans tried to come back as Rosenfels completed a 14-yard TD pass to WR Andre Johnson. However, the Vikings' defense stiffened for the win. QB Matt Schaub (21/29 for 224 yards and 1 interception), who started the game, left after the first half with a sprained left knee.\n[EX A]: How many incomplete passes did Matt Schaub throw?\n\n[EX Q]: Passage: The Cardinals' ninth game was an NFC West rivalry re-match against the Seahawks. In the first quarter the Cardinals took the early lead as RB Tim Hightower got a 2-yard TD run. The Seahawks replied with RB Marshawn Lynch getting a 1-yard TD run. The Cardinals trailed with kicker Olindo Mare getting a 41-yard field goal, but they answed back with kicker Jay Feely nailing a 23-yard field goal. The Cardinals struggled further with QB Matt Hasselbeck completing a 63-yard TD pass to WR Deon Butler. This was followed in the third quarter by a 34, 19 and 23-yard field goal from Mare. In the fourth quarter Mare got another 19-yard field goal to put the Seahawks up 29-10. The Cardinals responded with QB Derek Anderson making a 2-yard TD pass to WR Early Doucet (With a successful 2-point conversion as Anderson found WR Larry Fitzgerald), but the Seahawks put the game away with RB Justin Forsett getting a 4-yard TD run.\n[EX A]: From what yard line did both kickers kick a field goal?\n\n[EX Q]: Passage: Playing their third consecutive home game, the Patriots tried to improve their record to 15-0 against the 1-13 Dolphins. For the first time of the season, 15-year wide receiver Troy Brown was active; he saw action early in the game, returning a Dolphins punt on their first drive 10&#160;yards. The Patriots' second first down of their first possession was their 349th of the season, breaking their 1994 franchise record. Six plays later, Brady connected with Moss for an 11-yard touchdown and a 7-0 Patriots lead. After three punts, the Patriots' third drive of the game began on the final play of the first quarter, a 51-yard Maroney rush to give the Patriots the ball at the Dolphins' 28-yard line. After a successful third-down conversion, Brady threw his second touchdown pass of the game to Moss from a yard out to give the Patriots a 14-0 lead. The Dolphins' punted again on their next drive, and the Patriots opened up a 21-point lead with a 59-yard Maroney touchdown run while also setting the franchise record for net yards on a season, breaking the record of 5,965 set in 1978. After the Dolphins' fourth three-and-out of the game, a 38-yard Brandon Fields punt was muffed by Troy Brown and recovered by the Dolphins, who punted again three plays later. After moving the ball from their own 20-yard line to the Dolphins' 48-yard line, Brady completed a 48-yard touchdown pass to Gaffney on the Patriots' 71st touchdown of the season, breaking the NFL record of 70 set by the 1984 Dolphins. The Dolphins drove the Patriots' 4-yard line with 21&#160;seconds remaining in the half, but Tedy Bruschi batted down a Lemon pass on fourth down intended for Justin Peelle to preserve the Patriots' 28-0 lead heading into halftime. On the opening drive of the second half, Welker caught his 101st pass of the season, tying the Patriots individual franchise record Brown set in 2001. On the next play, Brady was intercepted by Jason Allen the end zone on a pass intended for Moss. After a 22-yard Chatman rush began the Dolphins' ensuing drive, the Dolphins punted for the seventh time three plays later. On third down from their own 28-yard line, Brady threw his second interception of the game, this time picked off by linebacker Derrick Pope on a pass also intended for Moss. The Dolphins moved the ball on their next drive from their own 46-yard line to the Patriots' 1-yard line, where Lemon scrambled out of bounds short of the end zone on 4th and goal. The Dolphins challenged the ruling, which was upheld after review. The play gave the Patriots the ball from their own 1-yard line, where a three-and-out set up a 64-yard Hanson punt from the end zone, his longest of the season. A 22-yard Lorenzo Booker rush on the Dolphins' next possession helped bring the Dolphins' to the Patriots 21-yard line, where Lemon connected with Greg Camarillo to cut the Patriots lead to 28-7. The Patriots committed their fourth turnover of the game when Brady was strip-sacked by Joey Porter to give the Dolphins the ball at their own 28-yard line. Four punts and a scoreless fourth quarter later, the Patriots picked up their 15th win of the season as they improved to 15-0 and became the first 15-0 team in NFL history. The Patriots' 15th win matched the win totals of the 2004 Pittsburgh Steelers, 1998 Minnesota Vikings, 1985 Chicago Bears, and 1984 San Francisco 49ers, while their 15-0 regular season start was a first in NFL history. The Patriots' 6-0 record against division opponents was a franchise first. The win also marked the Patriots' 18th straight regular season victory since their December 2006 loss to the Dolphins, tying the Patriots' 2003-2004 NFL record.\n[EX A]:" }, { "from": "gpt", "value": "How many points did the Dolphins make it the second half?\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: Translate from English to Hindi.\nInput: He took my silver paper.\nOutput:" }, { "from": "gpt", "value": "उसने मेरा चांदी का कागज ले लिया." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a sentence in the Japanese and Central Khmer language. Your task is check if the Khamer sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".\n\nJapanese: 10代の時、私はシドニーに住んでいて、NRLに触れたので、当然、私はフットボール(サッカー)と共にこのゲームに強い興味を持っています。 \n Khamer: គណៈកម្មាការបោះឆ្នោតជាតិបាននិយាយថា បន្ទាប់ពី99.9 ភាគរយនៃសន្លឹតឆ្នោតត្រូវបានរាប់​ 51.5 ភាគរយ បោះឆ្នោតយល់ស្របនិង48.5ភាគរយបោះឆ្នោតប្រឆាំងដំណោះស្រាយនេះ។\n" }, { "from": "gpt", "value": "No" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are given a statement written in Bengali. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement . Output the word from the correct option .\n\nStatement: ২০১৮ সালের আগস্টে <MASK> কেরালা রাজ্যে অস্বাভাবিক বৃষ্টিপাতের ফলে বন্যার সৃষ্টি হয় এবং এর প্রভাবে রাজ্যটি ক্ষতিগ্রস্ত হয়। প্রায় গত এক শতাব্দীতে এটি ছিল কেরালার সবচেয়ে ভয়ঙ্কর বন্যা। এর ফলে ৪৮৩ জন মানুষের মৃত্যু ঘটে এবং ১৪ জন নিখোঁজ হয়। কমপক্ষে ৬,৬১,০০০ জন মানুষ বাকি বিশ্ব থেকে বিচ্ছিন্ন হয়ে পড়েছিল এবং রাজ্যের ১৪ টি জেলায় বন্যা ঘটে। \n\n Option A: যুক্তরাষ্ট্রের\n\n Option B: ভারতে\n\n Option C: ভারতের\n\n Option D: কেরল\nOutput:" }, { "from": "gpt", "value": "ভারতের" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given a sentence in the English language from the various articles. Your task is to translate the given English sentence into the Yoruba language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should have natural language and formal form. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. The output should keep those values intact and include the quotation marks around them as well. 3) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *SHOULD NOT* be translated. Keep them as they are in the translations. 4) Do not localize measurement units like miles to kilometers during your translation. 5) Note the input is in sentence case except for special placeholders. Do the same in your translations.\n--------\nQuestion: Dates: May 24-26, 2019\n\nAnswer: Déètì: May 24 sí 26, 2019\n\n\nQuestion: Also, the modern language used in this translation will make personal and family study more faith strengthening.”\n\nAnswer: Ìyẹn nìkan kọ́, èdè òde òní tá a fi túmọ̀ Bíbélì yìí á mú kó rọrùn láti lóye, bákan náà, á mú kí ìgbàgbọ́ wa túbọ̀ lágbára bá a ṣe ń lò ó fún ìdákẹ́kọ̀ọ́ àti ìjọsìn ìdílé.”\n\n\nQuestion: We sell guinea-corn, and with the guinea-corn money we buy guinea corn.\n\nAnswer:" }, { "from": "gpt", "value": "A ta bàbà a fowóo bàbà ra bàbà.\n\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Definition: You are given a sentence in Italian. Your job is to translate the Italian sentence into Galician.\nInput: (applausi) Se poteste camminare in una di queste stanze, vedreste questo.\nOutput:" }, { "from": "gpt", "value": "(Aplausos) Se entraran nalgunha destas estancias verían isto." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: In this task you're given two statements in Marathi. You must judge whether the second sentence is the cause or effect of the first one. The sentences are separated by a newline character. Output either the word 'cause' or 'effect' .\nQ: माळी आपली वनस्पती भरभराटीची होती. \n त्याने जमिनीत खत ठेवले.\nA:" }, { "from": "gpt", "value": "effect" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is located or can be found at/in/on the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.\n\nHead: PersonX acts on PersonY's behalf<sep>Tail: useless" }, { "from": "gpt", "value": "No" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: You are given a sentence in Persian. Your job is to translate the Farsi sentence into Italian.\nInput: اما فکرم را به گذشته ‌ ای می ‌ برم که آنها ، فردیت و ارتباط و عشق را به من یاد دادند ، اما فکرم را به گذشته ‌ ای می ‌ برم که آنها ، فردیت و ارتباط و عشق را به من یاد دادند ، و می ‌ دونم اینها چیزهایی هستند که نمی ‌ خوام با طبیعی بودن از دست ‌ شان بدم. و می ‌ دونم اینها چیزهایی هستند که نمی ‌ خوام با معمولی بودن از دست ‌ شان بدم.\nOutput:" }, { "from": "gpt", "value": "Ma ripenso alle cose che mi hanno insegnato sull'individualità, la comunicazione e l'amore, e mi rendo conto che sono cose che non vorrei cambiare con la normalità." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "A text is given in Hindi. Translate it from the Hindi language to the Urdu language. The translation must not omit or add information to the original sentence.\n\nQ: 08 مئی, 2019\n\nA: 08 मई, 2019\n****\nQ: یکم اپریل کو امبیڈکر کی سالگرہ کے موقعے پر وزیراعظم نے ہیلتھ اینڈ ویلفیئر سینٹر کا چھتیس گڑھ کے بیجاپور ضلع میں آیوشمان بھارت کے تحت افتتاح کیا تھا۔\n\nA: अम्बेडकर जयंती के अवसर पर अप्रैल में प्रधानमंत्री ने छत्तीसगढ़ के बीजापुर जिले में आयुष्मान भारत के तहत पहले 'स्वास्थ्य एवं कल्याण केंद्र' का उद्घाटन किया था।\n****\nQ: جناب نریندر مودی نے کہا کہ ہمالیہ کے پاس روحانیت ،مہم جوئی،سیاحت اور فطرت سے محبت کرنے والوں کو دینے کے لئے بہت کچھ ہے۔ وزیر اعظم نے ہر ایک کو یہاں آنے اور ہمالیہ کو دریافت کرنے کی دعوت دی۔\n\nA:" }, { "from": "gpt", "value": "श्री नरेन्द्र मोदी ने कहा कि हिमालय आध्यात्म, रोमांच पर्यटन और प्रकृति प्रेमी के लिए काफी कुछ दे सकता है\n****\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Definition: The input contains a debate topic, an argument on the topic and a keypoint, separated by \"<sep>\". Your task is to answer if the keypoint matches the argument and summarizes exactly what the argument means, in the context of the given topic.\nInput: Topic: We should ban the use of child actors<sep>Argument: We should ban the use of child actors since it puts so much pressure on them. they should be growing up with a stable life and just enjoy being a kid.<sep>Keypoint: Being a performer harms the child's education\nOutput:" }, { "from": "gpt", "value": "False" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Polish.\nQ: دون أي هراء مخادع ورائها. أقصد ، إنها كلها — عليك أن تكون في غاية النزاهة مع ما تقوم به إن كان سيشتغل حقا.\nA: " }, { "from": "gpt", "value": "Żadnych sztuczek nieuchwytnych dla obserwatorów. Musisz być bardzo uczciwy w tym, co robisz, jeśli chcesz być wiarygodny." } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Instructions: This task is in Spanish. Based on the given context, generate a question which can be answered by the given context. Generate a question that has more than 7 words. You can paraphrase the given context while forming the question.\n Suggestion: The question may involve starting question words like WHERE, WHEN, HOW, WHAT (in Spanish).\nInput: CONTEXT: 22 de noviembre de 2010 29 mineros que quedaron atrapados en una mina de carbón al suroeste de China, fueron rescatados sanos y salvos cerca del medio día de este lunes, inicialmente 35 mineros se encontraban en el yacimiento a la hora del accidente, pero 13 lograron escapar. Un equipo de rescate que ingresó para intentar llegar a los otros 22 mineros atrapados, también se sumo a la lista de desaparecidos. El accidente ocurrió a las 11 am hora local (03:00 UTC) del domingo en una mina de carbón llamada \"Batían\" de una empresa minera China que se encuentra en medio de una polémica por \"sacrificar la seguridad de sus trabajadores.\" El rescate inició cerca del medio día y tomó cerca de una hora sacar a los 29 hombres atrapados. En general los mineros salieron sin ningún problema grave de salud, pero si muy cansados y algo desorientados, médicos prevén que salgan del centro médico en las próximas horas. Este accidente se suma a otros que han ocurrido en lo que va del 2010, uno de lo más recordados fue el \"Accidente en el yacimiento de la mina San José\", al norte de Chile, donde 33 hombres quedaron atrapados a más de 700 metros de profundidad por casi de 70 días. Actualmente 29 personas se encuentran atrapadas en una mina en Nueva Zelanda, donde los cuerpos de socorro temen encontrar algunos muertos puesto que las condiciones son muy delicadas y las posibilidades de un rescate efectivo se ven disminuidos.\nANSWER: norte de Chile\nOutput:" }, { "from": "gpt", "value": "¿Dónde está la mina San José?" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Definition: A text is given in English. Translate it from the English language to the Panjabi language. The translation must not omit or add information to the original sentence.\nInput: ਮੇਰੇ ਦੇਸ਼ਵਾਸੀਓ,\nOutput:" }, { "from": "gpt", "value": "Ladies and Gentlemen, and" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you are given product reviews about dvds. The goal is to classify the review as \"POS\" if the overall sentiment of the review is positive(the reviewer is satisfied) or as \"NEG\" if the overall sentiment of the review is negative(the reviewer is not satisfied).\n\nExample Input: A nice film by Lasse Hallström . This review is for the Criterion Collection DVD edition of the film. \"My Life as a Dog\" known in Sweden as \"Mitt Liv Som Hund\" is inarguably Hallström's best known foreign language film. Though he has done other films they are American or British made. \"Chocolat,\" \"What's Eating Gilbert Grape,\" and \"Something to Talk About.\" He is also very well known for directing the music videos for the world famous Swedish pop group, ABBA. The film is about a 12 year old boy in 1950's Sweden. He is very rambunctious and when his mother falls ill, his antics prevent her from recovering, so he is sent to live with his uncle. He meets new people there and makes friends with the towspeople. He often compares his misfortunes with those worse off than he is. The film has some excelent scenes of the more rural areas Sweden and some fine photography also. It remains a very popular film to this day and has recieved or been nominated for many awards. It won a golden globe for best foreign film and was nominated for best director by the AMPAS. Though it is described by many people as a family film, it got a PG-13 rating in the US. Mainly for nudity and sexual diaglogue. There is a half second of full frontal female nudity, though non-sexual, it still may be a cause for parental concern. The other scene involves material that I feel uncomfortable mentioning but parents are urged to watch the film themselves before letting their children see it. The special features on the Criterion DVD include Lasse Hallström's first film, \"Ska vi gå hem till dej eller till mej eller var och en till sitt?\" which translates to, \"Shall We Go to My Place or Your Place or Each Go Home Alone?\" This film has some explicit sex scenes and definately not appropriate for children. There is also a theatrical trailer and an interview with Lasse Hallström. The liner notes also include a special notation about the film by Kurt Vonnegut. Fans of Swedish cinema will enjoy this release\nExample Output: POS\n\nExample Input: 4 1/2 Stars Jessica Alba in a Bikini! A Must See . Jared (Paul Walker) and Sam (Jessica Alba) are a pair of salvagers living a poor but mostly happy existence on the shores of the Bahamas waiting for that day when they'll finally find the sunken treasure ship that will solve all their problems. When Jared's old friend Bryce (Scott Caan) arrives on the island to relax it looks like their dreams will come true when they find the wreckage of the pirate ship Zephyr. Unfortunately, the Zephyr is resting next to the a crashed drug plane carrying 800 kilos of cocaine... cocaine its owner (James Frain) wants back. Into The Blue has Great Acting, Good Directing, Great Special Effects, and Good Writing. Let me start off with saying I definitely prefer Paul Walker not driving fast cars and this film just proves I'm right. The Acting in this film has got to be its strongest point Jessica Alba does another great job in her third movie of 2005 and Paul Walker does a great job as well. Scoot Cann also has a standout performance as the standalone jerk! The Special Effects were probably the second best aspect because since basically all of it was underwater they did a very exceptional job like with the explosions and stuff. The Writing and Directing were also very good but I believe the Acting stood out the most. Overall if you like Jessica Alba or Paul Walker or Underwater Adventures You'll love this movi\nExample Output: POS\n\nExample Input: Great content - lousy packaging! . I'm in the UK and therefore it cost me quite a lot to have this package shipped over the Atlantic but it's the only way to see this series until way into next year. As has been reported below the packaging is very poor because the DTS disc (the very one I want) is not secured correctly on the double disc spindle and has been bouncing around for the last 4000 miles! The disc surface is now scratched and damaged. I see no point in sending it back to Amazon for replacement because the chances are it'll happen again so I'll have to try and get it repaired which is a nuisance. This item would have got five stars were it not for this problem and it's a great shame\nExample Output:" }, { "from": "gpt", "value": "POS\n\n" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Arabic. Your job is to translate the Arabic sentence into English.\nSee one example below:\nProblem: (تصفيق) ومع ذلك هناك معارك سياسية في بلدنا.\nSolution: (Applause) However there is a political battle in our country.\nExplanation: The Arabic sentence is correctly translated into English, because the meaning is preserved.\n\nProblem: أصبحت آخذ فاكهتي وأقتلع الملصق بأظافري وأحاول رميه ، فتساءلت بعدها: \"هل هناك ملصق غيره ؟\"\nSolution:" }, { "from": "gpt", "value": "I simply picked up the piece of fruit, dug at it with my nails, tried to flick it off, and then wondered, \"Was there another sticker?\"" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given a question, along with three passages, 1, 2, and 3. Your job is to determine which passage can be used to answer the question by searching for further information using terms from the passage. Indicate your choice as 1, 2, or 3.\n\nQuestion: How many pilots belong to the Finnish Air Force? Passage 1:University College Dublin A.F.C. was founded in 1895 as the Catholic University Medical School Football Club. They began playing regular games the following year. A First XI played College games against other Universities and a Second XI entered outside competitions. The club was founder members of the Leinster Junior League in 1896 and reached the semi-finals of the Leinster Senior Cup in 1897. The club became University College Dublin when the new University annexed the Medical school in 1908. UCD won the inaugural Intervarsities competition, the Collingwood Cup, in 1914 and added the Irish Intermediate Cup the following year beating Portadown 2–1 in a replayed final. When the Irish Free State was formed in 1921 and the new Football Association of Ireland was formed, UCD participated in the Preliminary round against fellow non-League team Shamrock Rovers in November 1921. The game took place in Windy Arbour and the Hoops won 6–2. UCD were invited to join the League of Ireland in 1922, but had to turn it down on the basis of not being able to field a team in the League of Ireland Shield in September as the Academic year didn't commence until October. In 1945 they won the FAI Intermediate Cup when UCD beat fellow future League of Ireland members Cobh Ramblers 4–2 in the final. UCD appeared in the FAI Cup in the 1930s, 1940s and 1950s, their final appearance as a non-League outfit coming in 1957 when Cork Athletic beat UCD 4–2 in the Mardyke.\n Passage 2:Tom Blackburn became ill with terminal lung cancer during the 1963–64 season. Don Donoher, a former Dayton player and assistant coach took over for the final three games of the 1963–64 season. Donoher, with Assistant Coach Chuck Grigsby, guided the Flyers to the NCAA Sweet Sixteen in his first two years as coach; they then led the Flyers to the 1967 NCAA Championship game by beating Western Kentucky, #8 ranked Tennessee, Virginia Tech, and #4 ranked North Carolina, before falling to #1 ranked and eventual champion UCLA 79–64 in the final. Donoher's 1967–68 squad began the season ranked #6 in the country in the AP Poll, but faltered in early competition and finished with a 17–9 record, missing the NCAA tournament. Nonetheless, Donoher's Flyers made a successful run through the 1968 NIT field, besting Kansas in the championship to win their second NIT crown. The Flyers would again face UCLA in a pivotal NCAA tournament game in 1974. The 20–7 Flyers squared off against the Bruins in the West Regional Sweet Sixteen and took the Bill Walton-led seven consecutive NCAA Champions to three overtimes before eventually falling 111–100. Donoher would again lead the Flyers to NCAA success in 1984 as Roosevelt Chapman led Flyers bested LSU, #7 ranked Oklahoma, and #15 ranked Washington before falling in the Elite Eight to eventual national champion Georgetown. The 24-season Donoher era was arguably Dayton's finest, producing eight NCAA tournament invitations, and eight NIT invitations. Following the success of the 1967 National Runner Up squad, the University began planning for a new 13,500 seat facility to house the nationally prominent Flyers. The UD Arena became the Flyer's home court at the start of the 1969–70 season.\n Passage 3:Somersalo was educated at the University of Helsinki before studying natural sciences at the University of Jena. Based in Germany during the First World War he enrolled in the German Army as an officer in 1916, serving until the armistice. He would later claim that the war had been the death of old Europe and argued that one of its main positives was that it had \"rescued our nation from the deadly, slimy embrace of a lothsome cuttlefish\" in reference to Russia. He transferred straight to the Finnish Army and from 1920 to 1926 was the commander of the Finnish Air Force.\n\n" }, { "from": "gpt", "value": "3" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "In this task, you will be shown a Persian passage and a question, and you have to determine whether the question is answerable based on the passage or not. If the question is answerable, choose the \"True\" label, and if not select \"False\"\nOne example is below.\nQ: فتوسنتز فرایندی زیست‌شیمیایی است که در آن، انرژی نورانی خورشید توسط گیاهان و برخی از باکتری‌ها به انرژی شیمیایی ذخیره‌شده در مواد غذایی آن‌ها تبدیل می‌شود. کمابیش همهٔ جانداران روی زمین به آن وابسته‌اند. در عمل فتوسنتز، اندام‌هایی مانند برگ که دارای سبزینه هستند، کربن دی‌اکسید، آب و نور را جذب کرده و به کلروپلاست می‌رسانند. طی واکنش‌هایی که درون کلروپلاست انجام می‌گیرد، این مواد به اکسیژن و کربوهیدرات‌ها تبدیل می‌شوند. همه اکسیژن کنونی موجود بر روی زمین، فراوردهٔ فتوسنتز است. برخی از کربوهیدرات‌های مهم تولیدشده مانند گلوکز، می‌توانند به دیگر مواد آلی، لیپیدها، نشاسته، سلولز و پروتئین تبدیل شوند که برای تبدیل‌شدن به پروتئین، نیاز به نیتروژن دارند. ژان باپتیست ون هلمونت، یکی از نخستین آزمایش‌های مربوط به فتوسنتز را انجام داد. همه بخش‌های سبزرنگ گیاه، قادر به انجام عمل فتوسنتز هستند. مادهٔ سبز موجود در گیاهان که سبزینه یا کلروفیل نام دارد، آغازکنندهٔ واکنش‌های فتوسنتز است. فتوسنتز در اندام‌هایی که فاقد سبزینه هستند، انجام نمی‌گیرد. \n Question: فتوسنتز چه نوع فرایندیه؟\nA: True\nRationale: This is a good example. The question is answerable based on the passage.\nQ: پول یا در فارسی افغانستان پیسه در تعریف ابتدایی آن وسیله، شیء، یا چیزی‌ست که انسان‌ها برای تسهیل در دادوستد خدمات و کالاها در راستای رفع نیازها و خواسته‌های خود از آن استفاده می‌کنند. در بیش‌تر کشورهای دنیا پول در گردش دارای دو بخش پول مسکوک و پول بانکی است که پول بانکی اکثریت مقدار پول در گردش را تشکیل می‌دهد. مردم نیز به اعتبار رژیم سیاسی حاکم و تولید ناخالص داخلی، پول چاپ شده را برای مبادله معتبر می‌دانند. حجم پول آثار کاملاً بارزی در اقتصاد داشته و بر نرخ تورم، بهره، بیکاری و تولید تأثیرگذار است. در مفهوم اقتصادی پول واحدی برای اندازه‌گیری تولید اقتصادی و نیز واحدی برای ذخیره ارزش اقتصادی می‌باشد. پول بی‌پشتوانه (پول فیات) پولی است که فاقد هرگونه ارزش ذاتی بوده و ارزش آن تنها وابسته به حکومت است. پولیس پولی بودکه بامس ساخته می‌شد. بعضی‌از علمای لغت می‌گویند کلمه پولس در آغاز در فنیقیه وضع شد و از آنجا به کشورهای دیگر سرایت کرد و کلمه فلوس که هنوز در برخی از کشورهای خاور نزدیک و خاورمیانه مصطلح است همین پولس است و کلمه پول که در زبان فارسی امروزی متداول است از ریشه پولوس گرفته شده‌است \n Question: پول در گردش یعنی چه؟\nA:" }, { "from": "gpt", "value": "False" } ]
Flan: Non English
chosen
[ { "from": "human", "value": "Given a sentence in Vietnamese, generate a new Vietnamese sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\nExample input: Anh đang muốn lấy một cái mũ trong một cái hộp.\nExample output: Anh không sao cả khi nhìn thấy một cái mũ trong một cái hộp.\nExample explanation: This is a good change in the input. The created sentence is semantically similar to the input as both are talking about a hat in a box and the changes in the sentence follows the commonsense knowledge.\nQ: Rất có thể bạn sẽ tìm được một học viên trong lớp.\nA:" }, { "from": "gpt", "value": "Rất có thể bạn sẽ tìm thấy một người học ở Cô - rinh - tô." } ]
Flan: Non English
chosen
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
331