Pre-training with Meta Learning for Chinese Word Segmentation

Zhen Ke, Liang Shi, Songtao Sun, Erli Meng, Bin Wang, Xipeng Qiu


Abstract
Recent researches show that pre-trained models (PTMs) are beneficial to Chinese Word Segmentation (CWS). However, PTMs used in previous works usually adopt language modeling as pre-training tasks, lacking task-specific prior segmentation knowledge and ignoring the discrepancy between pre-training tasks and downstream CWS tasks. In this paper, we propose a CWS-specific pre-trained model MetaSeg, which employs a unified architecture and incorporates meta learning algorithm into a multi-criteria pre-training task. Empirical results show that MetaSeg could utilize common prior segmentation knowledge from different existing criteria and alleviate the discrepancy between pre-trained models and downstream CWS tasks. Besides, MetaSeg can achieve new state-of-the-art performance on twelve widely-used CWS datasets and significantly improve model performance in low-resource settings.
Anthology ID:
2021.naacl-main.436
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5514–5523
Language:
URL:
https://aclanthology.org/2021.naacl-main.436
DOI:
10.18653/v1/2021.naacl-main.436
Bibkey:
Cite (ACL):
Zhen Ke, Liang Shi, Songtao Sun, Erli Meng, Bin Wang, and Xipeng Qiu. 2021. Pre-training with Meta Learning for Chinese Word Segmentation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5514–5523, Online. Association for Computational Linguistics.
Cite (Informal):
Pre-training with Meta Learning for Chinese Word Segmentation (Ke et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.436.pdf
Video:
 https://aclanthology.org/2021.naacl-main.436.mp4