Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation
This work addresses the challenge of making NLP technology accessible for thousands of under-served languages, though it is incremental as it builds on existing methods with new resources.
The paper tackles the problem of extending multilingual pretrained models to under-represented languages with limited textual data by using bilingual lexicons to synthesize data, resulting in improvements of up to 5 and 15 points on tasks for 19 languages.
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