Hsiu-Wen Li


2023

pdf
Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer
Hsiu-Wen Li | Ying-Jia Lin | Yi-Ting Li | Chun Lin | Hung-Yu Kao
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Unsupervised Chinese word segmentation (UCWS) has made progress by incorporating linguistic knowledge from pre-trained language models using parameter-free probing techniques. However, such approaches suffer from increased training time due to the need for multiple inferences using a pre-trained language model to perform word segmentation. This work introduces a novel way to enhance UCWS performance while maintaining training efficiency. Our proposed method integrates the segmentation signal from the unsupervised segmental language model to the pre-trained BERT classifier under a pseudo-labeling framework. Experimental results demonstrate that our approach achieves state-of-the-art performance on the eight UCWS tasks while considerably reducing the training time compared to previous approaches.