Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity Recognition

TL;DR

This paper introduces GLoDe, a framework that denoises pseudo labels using global and local information to improve cross-lingual NER, incorporating language-specific features for better generalization.

Contribution

The paper proposes a novel denoising strategy and emphasizes the importance of target language-specific features in cross-lingual NER.

Findings

GLoDe outperforms state-of-the-art methods on benchmark datasets.

The denoising strategy effectively reduces label noise.

Incorporating language-specific features improves model performance.

Abstract

Cross-lingual named entity recognition (NER) aims to train an NER model for the target language leveraging only labeled source language data and unlabeled target language data. Prior approaches either perform label projection on translated source language data or employ a source model to assign pseudo labels for target language data and train a target model on these pseudo-labeled data to generalize to the target language. However, these automatic labeling procedures inevitably introduce noisy labels, thus leading to a performance drop. In this paper, we propose a Global-Local Denoising framework (GLoDe) for cross-lingual NER. Specifically, GLoDe introduces a progressive denoising strategy to rectify incorrect pseudo labels by leveraging both global and local distribution information in the semantic space. The refined pseudo-labeled target language data significantly improves the model's generalization ability. Moreover, previous methods only consider improving the model with language-agnostic features, however, we argue that target language-specific features are also important and should never be ignored. To this end, we employ a simple auxiliary task to achieve this goal. Experimental results on two benchmark datasets with six target languages demonstrate that our proposed GLoDe significantly outperforms current state-of-the-art methods.