Update README.md

README.md

@@ -1,3 +1,37 @@
 ---
 license: mit
 ---
+# Model description 
+LegalBert is a BERT-base-cased model fine-tuned on a subset of the `case.law` corpus. Further details can be found in this paper:
+
+[A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering](http://ceur-ws.org/Vol-2645/paper5.pdf)  
+Nils Holzenberger, Andrew Blair-Stanek and Benjamin Van Durme  
+*Proceedings of the 2020 Natural Legal Language Processing (NLLP) Workshop, 24 August 2020*
+
+# Usage
+```
+from transformers import AutoModel, AutoTokenizer
+model = AutoModel.from_pretrained("jhu-clsp/LegalBert")
+tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/LegalBert")
+```
+
+# Citation
+```
+@inproceedings{holzenberger20dataset,
+  author    = {Nils Holzenberger and
+               Andrew Blair{-}Stanek and
+               Benjamin Van Durme},
+  title     = {A Dataset for Statutory Reasoning in Tax Law Entailment and Question
+               Answering},
+  booktitle = {Proceedings of the Natural Legal Language Processing Workshop 2020
+               co-located with the 26th {ACM} {SIGKDD} International Conference on
+               Knowledge Discovery {\&} Data Mining {(KDD} 2020), Virtual Workshop,
+               August 24, 2020},
+  series    = {{CEUR} Workshop Proceedings},
+  volume    = {2645},
+  pages     = {31--38},
+  publisher = {CEUR-WS.org},
+  year      = {2020},
+  url       = {http://ceur-ws.org/Vol-2645/paper5.pdf},
+}
+```