CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition
This addresses label noise issues in cross-lingual NER, improving generalization for distant languages, but it is incremental as it builds on existing translation and distillation methods.
The paper tackles label noise in cross-lingual named entity recognition by proposing CoLaDa, a collaborative label denoising framework that uses model and instance collaboration strategies, achieving superior results on benchmark datasets, particularly for distant languages.
Cross-lingual named entity recognition (NER) aims to train an NER system that generalizes well to a target language by leveraging labeled data in a given source language. Previous work alleviates the data scarcity problem by translating source-language labeled data or performing knowledge distillation on target-language unlabeled data. However, these methods may suffer from label noise due to the automatic labeling process. In this paper, we propose CoLaDa, a Collaborative Label Denoising Framework, to address this problem. Specifically, we first explore a model-collaboration-based denoising scheme that enables models trained on different data sources to collaboratively denoise pseudo labels used by each other. We then present an instance-collaboration-based strategy that considers the label consistency of each token's neighborhood in the representation space for denoising. Experiments on different benchmark datasets show that the proposed CoLaDa achieves superior results compared to previous methods, especially when generalizing to distant languages.