Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer
Hsiu-Wen Li, Ying-Jia Lin, Yi-Ting Li, Chun Yi Lin, Hung-Yu Kao
Abstract
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.
BibTeX
@inproceedings{
li2023improved,
title={Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer},
author={Hsiu-Wen Li and Ying-Jia Lin and Yi-Ting Li and Chun Yi Lin and Hung-Yu Kao},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=RXIYmRUWGD}
}