Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation

TL;DR

This paper introduces a novel approach combining distant annotation and adversarial training to improve cross-domain Chinese word segmentation, effectively addressing domain shift and OOV issues without requiring target domain supervision.

Contribution

The paper proposes an automatic distant annotation mechanism and a sentence-level adversarial training method for cross-domain CWS, enhancing robustness without target domain supervision.

Findings

Significantly outperforms previous methods on multiple datasets.

Effectively explores domain-specific words without supervision.

Reduces performance drop in out-of-domain scenarios.

Abstract

Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS). Nevertheless, the performance of supervised models tends to drop dramatically when they are applied to out-of-domain data. Performance degradation is caused by the distribution gap across domains and the out of vocabulary (OOV) problem. In order to simultaneously alleviate these two issues, this paper proposes to couple distant annotation and adversarial training for cross-domain CWS. For distant annotation, we rethink the essence of "Chinese words" and design an automatic distant annotation mechanism that does not need any supervision or pre-defined dictionaries from the target domain. The approach could effectively explore domain-specific words and distantly annotate the raw texts for the target domain. For adversarial training, we develop a sentence-level training procedure to perform noise reduction and maximum utilization of the source domain information. Experiments on multiple real-world datasets across various domains show the superiority and robustness of our model, significantly outperforming previous state-of-the-art cross-domain CWS methods.