MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages

Gokul Karthik Kumar, Abhishek Gehlot, Sahal Shaji Mullappilly, Karthik Nandakumar


Abstract
Accuracy of English-language Question Answering (QA) systems has improved significantly in recent years with the advent of Transformer-based models (e.g., BERT). These models are pre-trained in a self-supervised fashion with a large English text corpus and further fine-tuned with a massive English QA dataset (e.g., SQuAD). However, QA datasets on such a scale are not available for most of the other languages. Multi-lingual BERT-based models (mBERT) are often used to transfer knowledge from high-resource languages to low-resource languages. Since these models are pre-trained with huge text corpora containing multiple languages, they typically learn language-agnostic embeddings for tokens from different languages. However, directly training an mBERT-based QA system for low-resource languages is challenging due to the paucity of training data. In this work, we augment the QA samples of the target language using translation and transliteration into other languages and use the augmented data to fine-tune an mBERT-based QA model, which is already pre-trained in English. Experiments on the Google ChAII dataset show that fine-tuning the mBERT model with translations from the same language family boosts the question-answering performance, whereas the performance degrades in the case of cross-language families. We further show that introducing a contrastive loss between the translated question-context feature pairs during the fine-tuning process, prevents such degradation with cross-lingual family translations and leads to marginal improvement. The code for this work is available at https://github.com/gokulkarthik/mucot.
Anthology ID:
2022.dravidianlangtech-1.3
Volume:
Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
DravidianLangTech
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15–24
Language:
URL:
https://aclanthology.org/2022.dravidianlangtech-1.3
DOI:
10.18653/v1/2022.dravidianlangtech-1.3
Bibkey:
Cite (ACL):
Gokul Karthik Kumar, Abhishek Gehlot, Sahal Shaji Mullappilly, and Karthik Nandakumar. 2022. MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages. In Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages, pages 15–24, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages (Kumar et al., DravidianLangTech 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.dravidianlangtech-1.3.pdf
Video:
 https://aclanthology.org/2022.dravidianlangtech-1.3.mp4
Code
 gokulkarthik/mucot
Data
ChAII - Hindi and Tamil Question AnsweringSQuAD