Update README.md

README.md

@@ -121,6 +121,29 @@ The model architecture and config are the same as [M2M-100](https://huggingface.
 
 **Note**: SMALL100Tokenizer requires sentencepiece, so make sure to install it by ```pip install sentencepiece```
 
+# Supervised Training
+
+SMaLL-100 is a seq-to-seq model for the translation task. The input to the model is ```source:[tgt_lang_code] + src_tokens + [EOS]``` and ```target: tgt_tokens + [EOS]```. An example of supervised training is shown below:
+
+```
+from transformers import M2M100ForConditionalGeneration
+from tokenization_small100 import SMALL100Tokenizer
+
+model = M2M100ForConditionalGeneration.from_pretrained("alirezamsh/small100")
+tokenizer = M2M100Tokenizer.from_pretrained("alirezamsh/small100", tgt_lang="fr")
+
+src_text = "Life is like a box of chocolates."
+tgt_text = "La vie est comme une boîte de chocolat."
+
+model_inputs = tokenizer(src_text, text_target=tgt_text, return_tensors="pt")
+
+loss = model(**model_inputs).loss  # forward pass
+```
+
+Training data can be provided upon request.
+
+# Generation
+
 ```
 from transformers import M2M100ForConditionalGeneration
 from tokenization_small100 import SMALL100Tokenizer
@@ -146,7 +169,9 @@ tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
 # => "Life is like a box of chocolate."
 ```
 
-Please refer to [original repository](https://github.com/alirezamshi/small100) for further details.
+# Evaluation
+
+Please refer to [original repository](https://github.com/alirezamshi/small100) for spBLEU computation.
 
 # Languages Covered
 
@@ -156,10 +181,21 @@ Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bas
 
 If you use this model for your research, please cite the following work:
 ```
-@article{mohammadshahi2022small,
-  title={SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages},
-  author={Mohammadshahi, Alireza and Nikoulina, Vassilina and Berard, Alexandre and Brun, Caroline and Henderson, James and Besacier, Laurent},
-  journal={arXiv preprint arXiv:2210.11621},
-  year={2022}
+@misc{mohammadshahi2022small100,
+    title={SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages},
+    author={Alireza Mohammadshahi and Vassilina Nikoulina and Alexandre Berard and Caroline Brun and James Henderson and Laurent Besacier},
+    year={2022},
+    eprint={2210.11621},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+
+@misc{mohammadshahi2022compressed,
+    title={What Do Compressed Multilingual Machine Translation Models Forget?},
+    author={Alireza Mohammadshahi and Vassilina Nikoulina and Alexandre Berard and Caroline Brun and James Henderson and Laurent Besacier},
+    year={2022},
+    eprint={2205.10828},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
 }
 ```