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

by   Gokul Karthik Kumar, et al.

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


page 1

page 4

page 6


Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering

Human knowledge is collectively encoded in the roughly 6500 languages sp...

Towards More Equitable Question Answering Systems: How Much More Data Do You Need?

Question answering (QA) in English has been widely explored, but multili...

EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering

We propose EXAMS – a new benchmark dataset for cross-lingual and multili...

QAmeleon: Multilingual QA with Only 5 Examples

The availability of large, high-quality datasets has been one of the mai...

On the Usability of Transformers-based models for a French Question-Answering task

For many tasks, state-of-the-art results have been achieved with Transfo...

Few-shot Unified Question Answering: Tuning Models or Prompts?

Question-answering (QA) tasks often investigate specific question types,...

Multilingual Answer Sentence Reranking via Automatically Translated Data

We present a study on the design of multilingual Answer Sentence Selecti...

Please sign up or login with your details

Forgot password? Click here to reset