MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning

Authors

  • Ying Mo State Key Lab of Software Development Environment, Beihang University, Beijing, China
  • Jian Yang State Key Lab of Software Development Environment, Beihang University, Beijing, China
  • Jiahao Liu Meituan, Beijing, China
  • Qifan Wang Meta AI, New York, United States
  • Ruoyu Chen Beijing Information Science and Technology University, Beijing, China
  • Jingang Wang Meituan, Beijing, China
  • Zhoujun Li State Key Lab of Software Development Environment, Beihang University, Beijing, China

DOI:

https://doi.org/10.1609/aaai.v38i17.29843

Keywords:

NLP: Information Extraction, NLP: Syntax -- Tagging, Chunking & Parsing

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 relationships between pairs of tokens. This approach taps into the inherent contextual nuances of token-to-token connections within entities, allowing us to align representations across different languages. A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations. By enforcing agreement within both semantic and relational spaces, we minimize the gap between source sentences and their counterparts of both codeswitched and target sentences. This alignment extends to the relationships between diverse tokens, enhancing the projection of entities across languages. We further augment CrossNER by combining self-training with labeled source data and unlabeled target data. Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of MCL-NER over prior data-driven and model-based approaches. It achieves a substantial increase of nearly +2.0 F1 scores across a broad spectrum and establishes itself as the new state-of-the-art performer.

Published

2024-03-24

How to Cite

Mo, Y., Yang, J., Liu, J., Wang, Q., Chen, R., Wang, J., & Li, Z. (2024). MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(17), 18789-18797. https://doi.org/10.1609/aaai.v38i17.29843

Issue

Section

AAAI Technical Track on Natural Language Processing II