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.
BibTeX
@inproceedings{ke-etal-2021-pre,
title = "Pre-training with Meta Learning for {C}hinese Word Segmentation",
author = "Ke, Zhen and
Shi, Liang and
Sun, Songtao and
Meng, Erli and
Wang, Bin and
Qiu, Xipeng",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.436/",
doi = "10.18653/v1/2021.naacl-main.436",
pages = "5514--5523"
}