Updated the model card a bit.

README.md

@@ -24,18 +24,20 @@ based on the Wikipedia subcorpus. Evaluation of the full model will appear in a
 
 ## Eval results
 
-When fine-tuned (via `BertForTokenClassification`) on chunking and NER, the model outperforms multilingual BERT, achieves state-of-the-art results on the
-former task and comes within 0.5% F1 to the SotA on the latter. The exact scores are
+When fine-tuned (via `BertForTokenClassification`) on chunking and NER, the model outperforms multilingual BERT, achieves state-of-the-art results on
+both tasks. The exact scores are
 
 | NER | Minimal NP | Maximal NP |
 |-----|------------|------------|
-| 97.62% | **97.14%** | **96.97%** |
+| **97.62%** | **97.14%** | **96.97%** |
 
 ### BibTeX entry and citation info
 
-The training corpus, parameters and the evaluation methods are discussed in the
-[following PhD thesis](https://hlt.bme.hu/en/publ/nemeskey_2020):
+If you use the model, please cite the following papers:
 
+[Nemeskey, Dávid Márk (2020). "Natural Language Processing Methods for Language Modeling." PhD Thesis. Eötvös Loránd University.](https://hlt.bme.hu/en/publ/nemeskey_2020)
+
+Bibtex:
 ```bibtex
 @PhDThesis{ Nemeskey:2020,
   author = {Nemeskey, Dávid Márk},
@@ -44,3 +46,17 @@ The training corpus, parameters and the evaluation methods are discussed in the
   school = {E\"otv\"os Lor\'and University}
 }
 ```
+
+[Nemeskey, Dávid Márk (2021). "Introducing huBERT." In: XVII. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2021). Szeged, pp. 3-14](https://hlt.bme.hu/en/publ/hubert_2021)
+
+Bibtex:
+```bibtex
+@InProceedings{ Nemeskey:2021a,
+  author = {Nemeskey, Dávid Márk},
+  title = {Introducing \texttt{huBERT}},
+  booktitle = {{XVII}.\ Magyar Sz{\'a}m{\'i}t{\'o}g{\'e}pes Nyelv{\'e}szeti Konferencia ({MSZNY}2021)},
+  year = 2021,
+  pages = {TBA},
+  address = {Szeged},
+}
+```