Barah Fazili


pdf bib
Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding
Barah Fazili | Preethi Jyothi
Proceedings of the 29th International Conference on Computational Linguistics

Multilingual pretrained models, while effective on monolingual data, need additional training to work well with code-switched text. In this work, we present a novel idea of training multilingual models with alignment objectives using parallel text so as to explicitly align word representations with the same underlying semantics across languages. Such an explicit alignment step has a positive downstream effect and improves performance on multiple code-switched NLP tasks. We explore two alignment strategies and report improvements of up to 7.32%, 0.76% and 1.9% on Hindi-English Sentiment Analysis, Named Entity Recognition and Question Answering tasks compared to a competitive baseline model.