Au sujet de ce document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Xinyi Wang
- sl:arxiv_num : 2203.09435
- sl:arxiv_published : 2022-03-17T16:48:22Z
- sl:arxiv_summary : 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@en
- sl:arxiv_title : Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation@en
- sl:arxiv_updated : 2022-04-06T12:47:10Z
- sl:bookmarkOf : https://arxiv.org/abs/2203.09435
- sl:creationDate : 2022-09-08
- sl:creationTime : 2022-09-08T11:17:10Z
Documents with similar tags (experimental)
Préférences...