mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning

arXiv:2308.09073v2 Announce Type: replace
Abstract: Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora, especially for non-English data. While prior efforts mainly focus on data-driven transfer methods, a significant aspect that has not been fully explored is aligning both semantic and token-level representations across diverse languages. In this paper, we propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (mCL-NER). Specifically, we reframe the CrossNER task into a problem of recognizing …

abstract arxiv challenges cross-lingual cs.cl data data-driven english focus multilingual ner performance prior recognition semantic stemming token transfer type via view