Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation

TL;DR

This paper explores how to extend multilingual pretrained models to many more languages by using bilingual lexicons to generate synthetic data, improving NLP performance for under-represented languages.

Contribution

It introduces strategies leveraging bilingual lexicons to synthesize data, enabling NLP models to better serve thousands of under-represented languages.

Findings

Up to 15-point performance improvements on 19 languages

Effective data synthesis methods using bilingual lexicons

Enhanced NLP capabilities for under-served languages

Abstract

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP as they have no or limited textual data. To expand possibilities of using NLP technology in these under-represented languages, we systematically study strategies that relax the reliance on conventional language resources through the use of bilingual lexicons, an alternative resource with much better language coverage. We analyze different strategies to synthesize textual or labeled data using lexicons, and how this data can be combined with monolingual or parallel text when available. For 19 under-represented languages across 3 tasks, our methods lead to consistent improvements of up to 5 and 15 points with and without extra monolingual text respectively. Overall, our study highlights how NLP methods can be adapted to thousands more languages that are under-served by current technology