model update

README.md

@@ -0,0 +1,176 @@
+---
+datasets:
+- tner/tweetner7
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: tner/twitter-roberta-base-dec2021-tweetner7-2020-2021-concat
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: tner/tweetner7/test_2021
+      type: tner/tweetner7/test_2021
+      args: tner/tweetner7/test_2021
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6447001005249637
+    - name: Precision
+      type: precision
+      value: 0.6234607906675308
+    - name: Recall
+      type: recall
+      value: 0.6674375578168362
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.5982200308213212
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.576608821080324
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.622268182336741
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7793353811784417
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.7536184921149276
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.8068694344859488
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: tner/tweetner7/test_2020
+      type: tner/tweetner7/test_2020
+      args: tner/tweetner7/test_2020
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6582010582010582
+    - name: Precision
+      type: precision
+      value: 0.671343766864544
+    - name: Recall
+      type: recall
+      value: 0.6455630513751947
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.619090119256277
+    - name: Precision (macro)
+      type: precision_macro
+      value: 0.6309214005692869
+    - name: Recall (macro)
+      type: recall_macro
+      value: 0.6088158080350003
+    - name: F1 (entity span)
+      type: f1_entity_span
+      value: 0.7647525800476317
+    - name: Precision (entity span)
+      type: precision_entity_span
+      value: 0.7802375809935205
+    - name: Recall (entity span)
+      type: recall_entity_span
+      value: 0.7498702646600934
+
+pipeline_tag: token-classification
+widget:
+- text: "Get the all-analog Classic Vinyl Edition of `Takin' Off` Album from {{@Herbie Hancock@}} via {{USERNAME}} link below: {{URL}}"
+  example_title: "NER Example 1"
+---
+# tner/twitter-roberta-base-dec2021-tweetner7-2020-2021-concat
+
+This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-dec2021](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021) on the 
+[tner/tweetner7](https://huggingface.co/datasets/tner/tweetner7) dataset (`train_all` split).
+Model fine-tuning is done via [T-NER](https://github.com/asahi417/tner)'s hyper-parameter search (see the repository
+for more detail). It achieves the following results on the test set of 2021:
+- F1 (micro): 0.6447001005249637
+- Precision (micro): 0.6234607906675308
+- Recall (micro): 0.6674375578168362
+- F1 (macro): 0.5982200308213212
+- Precision (macro): 0.576608821080324
+- Recall (macro): 0.622268182336741
+
+
+
+The per-entity breakdown of the F1 score on the test set are below:
+- corporation: 0.5048128342245989
+- creative_work: 0.45297029702970293
+- event: 0.46761313220940554
+- group: 0.6009661835748793
+- location: 0.6592252133946159
+- person: 0.8302430243024302
+- product: 0.6717095310136157 
+
+For F1 scores, the confidence interval is obtained by bootstrap as below:
+- F1 (micro): 
+    - 90%: [0.6358921767926183, 0.6542958612061787]
+    - 95%: [0.6341987223616053, 0.6560992650244356] 
+- F1 (macro): 
+    - 90%: [0.6358921767926183, 0.6542958612061787]
+    - 95%: [0.6341987223616053, 0.6560992650244356] 
+
+Full evaluation can be found at [metric file of NER](https://huggingface.co/tner/twitter-roberta-base-dec2021-tweetner7-2020-2021-concat/raw/main/eval/metric.json) 
+and [metric file of entity span](https://huggingface.co/tner/twitter-roberta-base-dec2021-tweetner7-2020-2021-concat/raw/main/eval/metric_span.json).
+
+### Usage
+This model can be used through the [tner library](https://github.com/asahi417/tner). Install the library via pip   
+```shell
+pip install tner
+```
+and activate model as below.
+```python
+from tner import TransformersNER
+model = TransformersNER("tner/twitter-roberta-base-dec2021-tweetner7-2020-2021-concat")
+model.predict(["Jacob Collier is a Grammy awarded English artist from London"])
+```
+It can be used via transformers library but it is not recommended as CRF layer is not supported at the moment.
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+ - dataset: ['tner/tweetner7']
+ - dataset_split: train_all
+ - dataset_name: None
+ - local_dataset: None
+ - model: cardiffnlp/twitter-roberta-base-dec2021
+ - crf: True
+ - max_length: 128
+ - epoch: 30
+ - batch_size: 32
+ - lr: 1e-05
+ - random_seed: 0
+ - gradient_accumulation_steps: 1
+ - weight_decay: 1e-07
+ - lr_warmup_step_ratio: 0.3
+ - max_grad_norm: 1
+
+The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/tner/twitter-roberta-base-dec2021-tweetner7-2020-2021-concat/raw/main/trainer_config.json).
+
+### Reference
+If you use any resource from T-NER, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
+
+```
+
+@inproceedings{ushio-camacho-collados-2021-ner,
+    title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
+    author = "Ushio, Asahi  and
+      Camacho-Collados, Jose",
+    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
+    month = apr,
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2021.eacl-demos.7",
+    doi = "10.18653/v1/2021.eacl-demos.7",
+    pages = "53--62",
+    abstract = "Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning. In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER. Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers. We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and cross- lingual performance across the datasets. The results from our initial experiments show that in-domain performance is generally competitive across datasets. However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if fine- tuned on a combined dataset. To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub.",
+}
+
+```

eval/metric.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.6582010582010582, "micro/f1_ci": {"90": [0.6379167890637253, 0.6767511315048438], "95": [0.6339207548025675, 0.6807947362204927]}, "micro/recall": 0.6455630513751947, "micro/precision": 0.671343766864544, "macro/f1": 0.619090119256277, "macro/f1_ci": {"90": [0.5972479198841049, 0.6386559386417274], "95": [0.5937401018540227, 0.6428463929597004]}, "macro/recall": 0.6088158080350003, "macro/precision": 0.6309214005692869, "per_entity_metric": {"corporation": {"f1": 0.5796344647519582, "f1_ci": {"90": [0.5234079697610352, 0.6277959240647681], "95": [0.5141152231379257, 0.6394375]}, "precision": 0.578125, "recall": 0.581151832460733}, "creative_work": {"f1": 0.553072625698324, "f1_ci": {"90": [0.49853196304809205, 0.6028253100693715], "95": [0.4876406133927624, 0.6114264896373057]}, "precision": 0.553072625698324, "recall": 0.553072625698324}, "event": {"f1": 0.444022770398482, "f1_ci": {"90": [0.3922253196193406, 0.4971993370807634], "95": [0.38228807543114435, 0.5075202210070632]}, "precision": 0.44656488549618323, "recall": 0.44150943396226416}, "group": {"f1": 0.5749128919860629, "f1_ci": {"90": [0.5205170817406994, 0.625659134872618], "95": [0.5104305259005177, 0.6358512874408828]}, "precision": 0.6273764258555133, "recall": 0.5305466237942122}, "location": {"f1": 0.6646706586826348, "f1_ci": {"90": [0.5974730765917118, 0.7278115556520639], "95": [0.5810510954741723, 0.7381043956043957]}, "precision": 0.6568047337278107, "recall": 0.6727272727272727}, "person": {"f1": 0.844331641285956, "f1_ci": {"90": [0.8183284457478005, 0.8676071424722781], "95": [0.8145682012390513, 0.8709331756339546]}, "precision": 0.8515358361774744, "recall": 0.837248322147651}, "product": {"f1": 0.6729857819905214, "f1_ci": {"90": [0.6212986836419078, 0.7170731707317073], "95": [0.6111074847693646, 0.725641560972215]}, "precision": 0.7029702970297029, "recall": 0.6454545454545455}}}

eval/{metric.json → metric.test_2021.json}

@@ -1 +1 @@
-{"2021.dev": {"micro/f1": 0.642156862745098, "micro/f1_ci": {}, "micro/recall": 0.655, "micro/precision": 0.6298076923076923, "macro/f1": 0.6004942384479613, "macro/f1_ci": {}, "macro/recall": 0.6146549344794797, "macro/precision": 0.5895253900625403, "per_entity_metric": {"corporation": {"f1": 0.5970149253731343, "f1_ci": {}, "precision": 0.6060606060606061, "recall": 0.5882352941176471}, "creative_work": {"f1": 0.42774566473988446, "f1_ci": {}, "precision": 0.37373737373737376, "recall": 0.5}, "event": {"f1": 0.38345864661654133, "f1_ci": {}, "precision": 0.37777777777777777, "recall": 0.3893129770992366}, "group": {"f1": 0.6458797327394209, "f1_ci": {}, "precision": 0.6531531531531531, "recall": 0.6387665198237885}, "location": {"f1": 0.6577181208053691, "f1_ci": {}, "precision": 0.6363636363636364, "recall": 0.6805555555555556}, "person": {"f1": 0.821917808219178, "f1_ci": {}, "precision": 0.7973421926910299, "recall": 0.8480565371024735}, "product": {"f1": 0.6697247706422017, "f1_ci": {}, "precision": 0.6822429906542056, "recall": 0.6576576576576577}}}, "2021.test": {"micro/f1": 0.6447001005249637, "micro/f1_ci": {"90": [0.6358921767926183, 0.6542958612061787], "95": [0.6341987223616053, 0.6560992650244356]}, "micro/recall": 0.6674375578168362, "micro/precision": 0.6234607906675308, "macro/f1": 0.5982200308213212, "macro/f1_ci": {"90": [0.5881550153814866, 0.6085554142266025], "95": [0.5868087805464741, 0.6101643811579637]}, "macro/recall": 0.622268182336741, "macro/precision": 0.576608821080324, "per_entity_metric": {"corporation": {"f1": 0.5048128342245989, "f1_ci": {"90": [0.479765110450545, 0.5306144595657036], "95": [0.47517387506462216, 0.5351675634581814]}, "precision": 0.4865979381443299, "recall": 0.5244444444444445}, "creative_work": {"f1": 0.45297029702970293, "f1_ci": {"90": [0.42319336176888755, 0.48488758755117906], "95": [0.4162047502047502, 0.4893898449722657]}, "precision": 0.4135593220338983, "recall": 0.5006839945280438}, "event": {"f1": 0.46761313220940554, "f1_ci": {"90": [0.44575807806932577, 0.4903905189360568], "95": [0.4422550278552021, 0.49587724619000695]}, "precision": 0.4562770562770563, "recall": 0.47952684258416745}, "group": {"f1": 0.6009661835748793, "f1_ci": {"90": [0.5801815329496189, 0.621933633730728], "95": [0.5775182443071706, 0.6251598548687218]}, "precision": 0.5879017013232514, "recall": 0.6146245059288538}, "location": {"f1": 0.6592252133946159, "f1_ci": {"90": [0.6323286497785727, 0.6864389614941666], "95": [0.6275471764048085, 0.6917652468518968]}, "precision": 0.6220570012391574, "recall": 0.7011173184357542}, "person": {"f1": 0.8302430243024302, "f1_ci": {"90": [0.8199438783116751, 0.841483594116568], "95": [0.8177798298118928, 0.8435008852333449]}, "precision": 0.8111150193457615, "recall": 0.8502949852507374}, "product": {"f1": 0.6717095310136157, "f1_ci": {"90": [0.6498440287017558, 0.6930412862784509], "95": [0.6467581027914819, 0.6969171035150417]}, "precision": 0.658753709198813, "recall": 0.6851851851851852}}}, "2020.test": {"micro/f1": 0.6582010582010582, "micro/f1_ci": {"90": [0.6379167890637253, 0.6767511315048438], "95": [0.6339207548025675, 0.6807947362204927]}, "micro/recall": 0.6455630513751947, "micro/precision": 0.671343766864544, "macro/f1": 0.619090119256277, "macro/f1_ci": {"90": [0.5972479198841049, 0.6386559386417274], "95": [0.5937401018540227, 0.6428463929597004]}, "macro/recall": 0.6088158080350003, "macro/precision": 0.6309214005692869, "per_entity_metric": {"corporation": {"f1": 0.5796344647519582, "f1_ci": {"90": [0.5234079697610352, 0.6277959240647681], "95": [0.5141152231379257, 0.6394375]}, "precision": 0.578125, "recall": 0.581151832460733}, "creative_work": {"f1": 0.553072625698324, "f1_ci": {"90": [0.49853196304809205, 0.6028253100693715], "95": [0.4876406133927624, 0.6114264896373057]}, "precision": 0.553072625698324, "recall": 0.553072625698324}, "event": {"f1": 0.444022770398482, "f1_ci": {"90": [0.3922253196193406, 0.4971993370807634], "95": [0.38228807543114435, 0.5075202210070632]}, "precision": 0.44656488549618323, "recall": 0.44150943396226416}, "group": {"f1": 0.5749128919860629, "f1_ci": {"90": [0.5205170817406994, 0.625659134872618], "95": [0.5104305259005177, 0.6358512874408828]}, "precision": 0.6273764258555133, "recall": 0.5305466237942122}, "location": {"f1": 0.6646706586826348, "f1_ci": {"90": [0.5974730765917118, 0.7278115556520639], "95": [0.5810510954741723, 0.7381043956043957]}, "precision": 0.6568047337278107, "recall": 0.6727272727272727}, "person": {"f1": 0.844331641285956, "f1_ci": {"90": [0.8183284457478005, 0.8676071424722781], "95": [0.8145682012390513, 0.8709331756339546]}, "precision": 0.8515358361774744, "recall": 0.837248322147651}, "product": {"f1": 0.6729857819905214, "f1_ci": {"90": [0.6212986836419078, 0.7170731707317073], "95": [0.6111074847693646, 0.725641560972215]}, "precision": 0.7029702970297029, "recall": 0.6454545454545455}}}, "2021.test (span detection)": {"micro/f1": 0.7793353811784417, "micro/f1_ci": {}, "micro/recall": 0.8068694344859488, "micro/precision": 0.7536184921149276, "macro/f1": 0.7793353811784417, "macro/f1_ci": {}, "macro/recall": 0.8068694344859488, "macro/precision": 0.7536184921149276}, "2020.test (span detection)": {"micro/f1": 0.7647525800476317, "micro/f1_ci": {}, "micro/recall": 0.7498702646600934, "micro/precision": 0.7802375809935205, "macro/f1": 0.7647525800476317, "macro/f1_ci": {}, "macro/recall": 0.7498702646600934, "macro/precision": 0.7802375809935205}}
+{"micro/f1": 0.6447001005249637, "micro/f1_ci": {"90": [0.6358921767926183, 0.6542958612061787], "95": [0.6341987223616053, 0.6560992650244356]}, "micro/recall": 0.6674375578168362, "micro/precision": 0.6234607906675308, "macro/f1": 0.5982200308213212, "macro/f1_ci": {"90": [0.5881550153814866, 0.6085554142266025], "95": [0.5868087805464741, 0.6101643811579637]}, "macro/recall": 0.622268182336741, "macro/precision": 0.576608821080324, "per_entity_metric": {"corporation": {"f1": 0.5048128342245989, "f1_ci": {"90": [0.479765110450545, 0.5306144595657036], "95": [0.47517387506462216, 0.5351675634581814]}, "precision": 0.4865979381443299, "recall": 0.5244444444444445}, "creative_work": {"f1": 0.45297029702970293, "f1_ci": {"90": [0.42319336176888755, 0.48488758755117906], "95": [0.4162047502047502, 0.4893898449722657]}, "precision": 0.4135593220338983, "recall": 0.5006839945280438}, "event": {"f1": 0.46761313220940554, "f1_ci": {"90": [0.44575807806932577, 0.4903905189360568], "95": [0.4422550278552021, 0.49587724619000695]}, "precision": 0.4562770562770563, "recall": 0.47952684258416745}, "group": {"f1": 0.6009661835748793, "f1_ci": {"90": [0.5801815329496189, 0.621933633730728], "95": [0.5775182443071706, 0.6251598548687218]}, "precision": 0.5879017013232514, "recall": 0.6146245059288538}, "location": {"f1": 0.6592252133946159, "f1_ci": {"90": [0.6323286497785727, 0.6864389614941666], "95": [0.6275471764048085, 0.6917652468518968]}, "precision": 0.6220570012391574, "recall": 0.7011173184357542}, "person": {"f1": 0.8302430243024302, "f1_ci": {"90": [0.8199438783116751, 0.841483594116568], "95": [0.8177798298118928, 0.8435008852333449]}, "precision": 0.8111150193457615, "recall": 0.8502949852507374}, "product": {"f1": 0.6717095310136157, "f1_ci": {"90": [0.6498440287017558, 0.6930412862784509], "95": [0.6467581027914819, 0.6969171035150417]}, "precision": 0.658753709198813, "recall": 0.6851851851851852}}}

eval/metric_span.test_2020.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7647525800476317, "micro/f1_ci": {}, "micro/recall": 0.7498702646600934, "micro/precision": 0.7802375809935205, "macro/f1": 0.7647525800476317, "macro/f1_ci": {}, "macro/recall": 0.7498702646600934, "macro/precision": 0.7802375809935205}

eval/metric_span.test_2021.json

@@ -0,0 +1 @@
+{"micro/f1": 0.7793353811784417, "micro/f1_ci": {}, "micro/recall": 0.8068694344859488, "micro/precision": 0.7536184921149276, "macro/f1": 0.7793353811784417, "macro/f1_ci": {}, "macro/recall": 0.8068694344859488, "macro/precision": 0.7536184921149276}

trainer_config.json

@@ -1 +1 @@
-{"data_split": "2020_2021.train", "model": "cardiffnlp/twitter-roberta-base-dec2021", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-05, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}
+{"dataset": ["tner/tweetner7"], "dataset_split": "train_all", "dataset_name": null, "local_dataset": null, "model": "cardiffnlp/twitter-roberta-base-dec2021", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-05, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}