Update README.md

README.md

@@ -1,3 +1,102 @@
 ---
-license: mit
+tags:
+- paraphrase-generation
+- multilingual
+- nlp
+- indicnlp
+datasets:
+- ai4bharat/IndicParaphrase
+language:
+- as
+- bn
+- gu
+- hi
+- kn
+- ml
+- mr
+- or
+- pa
+- ta
+- te
+licenses:
+- cc-by-nc-4.0
+
+
 ---
+
+# MultiIndicParaphraseGeneration
+
+This repository contains the [IndicBART](https://huggingface.co/ai4bharat/IndicBART) checkpoint finetuned on the 11 languages of [IndicParaphrase](https://huggingface.co/datasets/ai4bharat/IndicParaphrase) dataset. For finetuning details,
+see the [paper](https://arxiv.org/abs/2203.05437). 
+
+
+## Using this model in `transformers`
+
+```
+from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
+from transformers import AlbertTokenizer, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration", do_lower_case=False, use_fast=False, keep_accents=True)
+# Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration", do_lower_case=False, use_fast=False, keep_accents=True)
+model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration")
+# Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration")
+# Some initial mapping
+bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
+eos_id = tokenizer._convert_token_to_id_with_added_voc("</s>")
+pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
+# To get lang_id use any of ['<2as>', '<2bn>', '<2en>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']
+# First tokenize the input and outputs. The format below is how IndicBART was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>". 
+inp = tokenizer("I am a boy </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids # tensor([[  466,  1981,    80, 25573, 64001, 64004]])
+
+# For generation. Pardon the messiness. Note the decoder_start_token_id.
+model.eval() # Set dropouts to zero
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
+# Decode to get output strings
+decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(decoded_output) # I am a boy
+# Note that if your output language is not Hindi or Marathi, you should convert its script from Devanagari to the desired language using the Indic NLP Library.
+# What if we mask?
+inp = tokenizer("I am [MASK] </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
+decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(decoded_output) # I am happy
+inp = tokenizer("मैं [MASK] हूँ </s> <2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
+decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(decoded_output) # मैं जानता हूँ
+inp = tokenizer("मला [MASK] पाहिजे </s> <2mr>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
+decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
+print(decoded_output) # मला ओळखलं पाहिजे
+```
+
+## Benchmarks
+
+Scores on the `IndicParaphrase` test sets are as follows:
+
+Language | BLEU / Self-BLEU / iBLEU
+---------|----------------------------
+as | 1.66 / 2.06 / 0.54
+bn | 11.57 / 1.69 / 0.54
+gu | 22.10 / 2.76 / 7.59
+hi | 27.29 / 2.87 / 14.64
+kn | 15.40 / 2.98 / 18.24
+ml | 10.57 / 1.70 / 9.89
+mr | 20.38 / 2.20 / 6.89
+or | 19.26 / 2.10 / 13.61
+pa | 14.87 / 1.35 / 10.00
+ta | 18.52 / 2.88 / 12.10
+te | 16.70 / 3.34 / 10.69
+
+
+
+## Citation
+
+If you use this model, please cite the following paper:
+```
+@inproceedings{Kumar2022IndicNLGSM,
+  title={IndicNLG Suite: Multilingual Datasets for Diverse NLG Tasks in Indic Languages},
+  author={Aman Kumar and Himani Shrotriya and Prachi Sahu and Raj Dabre and Ratish Puduppully and Anoop Kunchukuttan and Amogh Mishra and Mitesh M. Khapra and Pratyush Kumar},
+  year={2022},
+  url = "https://arxiv.org/abs/2203.05437"
+  }
+```