Create README.md

README.md

@@ -0,0 +1,33 @@
+---
+language: 
+  - de
+  - fr
+  - en
+  - ro
+  - zh
+thumbnail: 
+tags:
+- sentence alignment
+license: bsd-3-clause
+---
+
+# AWESOME: Aligning Word Embedding Spaces of Multilingual Encoders
+
+This model comes from the following GitHub repository: [https://github.com/neulab/awesome-align](https://github.com/neulab/awesome-align)
+
+It corresponds to this paper: [https://arxiv.org/abs/2101.08231](https://arxiv.org/abs/2101.08231)
+
+Please cite the original paper if you decide to use the model: 
+
+```
+@inproceedings{dou2021word,
+  title={Word Alignment by Fine-tuning Embeddings on Parallel Corpora},
+  author={Dou, Zi-Yi and Neubig, Graham},
+  booktitle={Conference of the European Chapter of the Association for Computational Linguistics (EACL)},
+  year={2021}
+}
+```
+
+
+`awesome-align` is a tool that can extract word alignments from multilingual BERT (mBERT) [Demo](https://colab.research.google.com/drive/1205ubqebM0OsZa1nRgbGJBtitgHqIVv6?usp=sharing) and allows you to fine-tune mBERT on parallel corpora for better alignment quality (see our paper for more details).
+