Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment

arXiv:2404.02490v1 Announce Type: new
Abstract: The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word representation in low-resource languages is notably under-aligned with that in high-resource languages in current models. To address this, we introduce a novel framework that explicitly aligns words between English and eight low-resource languages, utilizing off-the-shelf word alignment models. This framework incorporates three primary training …

abstract alignment arxiv cross-lingual cs.cl current embedding embeddings languages low paper representation research shows type word