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

TL;DR

This paper introduces mCL-NER, a novel cross-lingual NER method using multi-view contrastive learning to align semantic and token-level representations across languages, significantly improving performance on the XTREME benchmark.

Contribution

It proposes a multi-view contrastive learning framework that aligns semantic and relational token representations for cross-lingual NER, surpassing prior data-driven methods.

Findings

Achieves nearly +2.0 F1 score improvement on XTREME benchmark.

Outperforms previous state-of-the-art approaches.

Effective in aligning token and semantic representations across 40 languages.

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 $F_1$ scores across a broad spectrum and establishes itself as the new state-of-the-art performer.