Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation
This addresses the cross-domain adaptation issue in Chinese word segmentation, which is crucial for NLP applications handling diverse text sources, though it appears incremental as it builds on existing neural and adversarial techniques.
The paper tackled the problem of performance degradation in Chinese word segmentation when applying supervised models to out-of-domain data, proposing a method that couples distant annotation and adversarial training to achieve significant improvements over previous state-of-the-art cross-domain methods.
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.