Gujarati-XLM-R-Large

Gujarati-XLM-R-Large

This model is finetuned over XLM-RoBERTa (XLM-R) using its large variant with the Gujarati language using the OSCAR monolingual dataset. We used the same masked language modelling (MLM) objective which was used for pretraining the XLM-R. As it is built over the pretrained XLM-R, we leveraged Transfer Learning by exploiting the knowledge from its parent model.

Dataset

OSCAR corpus contains several diverse datasets for different languages. We followed the work of CamemBERT who reported better performance with this diverse dataset as compared to the other large homogenous datasets.

Preprocessing and Training Procedure

Please visit this link for the detailed procedure.

Usage

• This model can be used for further finetuning for different NLP tasks using the Gujarati language.
• It can be used to generate contextualised word representations for the Gujarati words.
• It can be used for domain adaptation.
• It can be used to predict the missing words from the Gujarati sentences.

Demo

Using the model to predict missing words

from transformers import pipeline
unmasker = pipeline('fill-mask', model='ashwani-tanwar/Gujarati-XLM-R-Large')
pred_word = unmasker("અમદાવાદ એ ગુજરાતનું એક <mask> છે.")
print(pred_word) 

[{'sequence': '<s> અમદાવાદ એ ગુજરાતનું એક શહેર છે.</s>', 'score': 0.9790881276130676, 'token': 85227, 'token_str': '▁શહેર'}, 
{'sequence': '<s> અમદાવાદ એ ગુજરાતનું એક રાજ્ય છે.</s>', 'score': 0.004246668424457312, 'token': 63678, 'token_str': '▁રાજ્ય'}, 
{'sequence': '<s> અમદાવાદ એ ગુજરાતનું એક ગામ છે.</s>', 'score': 0.0038021174259483814, 'token': 66346, 'token_str': '▁ગામ'}, 
{'sequence': '<s> અમદાવાદ એ ગુજરાતનું એક મહત્વ છે.</s>', 'score': 0.002798238070681691, 'token': 126763, 'token_str': '▁મહત્વ'}, 
{'sequence': '<s> અમદાવાદ એ ગુજરાતનું એક અમદાવાદ છે.</s>', 'score': 0.0021192911081016064, 'token': 69499, 'token_str': '▁અમદાવાદ'}]

Using the model to generate contextualised word representations

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("ashwani-tanwar/Gujarati-XLM-R-Large")
model = AutoModel.from_pretrained("ashwani-tanwar/Gujarati-XLM-R-Large")
sentence = "અમદાવાદ એ ગુજરાતનું એક શહેર છે."
encoded_sentence = tokenizer(sentence, return_tensors='pt')
context_word_rep = model(**encoded_sentence)