Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision

Mieradilijiang Maimaiti, Yang Liu, Yuanhang Zheng, Gang Chen, Kaiyu Huang, Ji Zhang, Huanbo Luan, Maosong Sun


Abstract
Recent state-of-the-art (SOTA) effective neural network methods and fine-tuning methods based on pre-trained models (PTM) have been used in Chinese word segmentation (CWS), and they achieve great results. However, previous works focus on training the models with the fixed corpus at every iteration. The intermediate generated information is also valuable. Besides, the robustness of the previous neural methods is limited by the large-scale annotated data. There are a few noises in the annotated corpus. Limited efforts have been made by previous studies to deal with such problems. In this work, we propose a self-supervised CWS approach with a straightforward and effective architecture. First, we train a word segmentation model and use it to generate the segmentation results. Then, we use a revised masked language model (MLM) to evaluate the quality of the segmentation results based on the predictions of the MLM. Finally, we leverage the evaluations to aid the training of the segmenter by improved minimum risk training. Experimental results show that our approach outperforms previous methods on 9 different CWS datasets with single criterion training and multiple criteria training and achieves better robustness.
Anthology ID:
2021.emnlp-main.158
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2068–2077
Language:
URL:
https://aclanthology.org/2021.emnlp-main.158
DOI:
10.18653/v1/2021.emnlp-main.158
Bibkey:
Cite (ACL):
Mieradilijiang Maimaiti, Yang Liu, Yuanhang Zheng, Gang Chen, Kaiyu Huang, Ji Zhang, Huanbo Luan, and Maosong Sun. 2021. Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2068–2077, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision (Maimaiti et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.158.pdf