fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP

Zhichao Geng, Hang Yan, Xipeng Qiu, Xuanjing Huang


Abstract
We present fastHan, an open-source toolkit for four basic tasks in Chinese natural language processing: Chinese word segmentation (CWS), Part-of-Speech (POS) tagging, named entity recognition (NER), and dependency parsing. The backbone of fastHan is a multi-task model based on a pruned BERT, which uses the first 8 layers in BERT. We also provide a 4-layer base model compressed from the 8-layer model. The joint-model is trained and evaluated on 13 corpora of four tasks, yielding near state-of-the-art (SOTA) performance in dependency parsing and NER, achieving SOTA performance in CWS and POS. Besides, fastHan’s transferability is also strong, performing much better than popular segmentation tools on a non-training corpus. To better meet the need of practical application, we allow users to use their own labeled data to further fine-tune fastHan. In addition to its small size and excellent performance, fastHan is user-friendly. Implemented as a python package, fastHan isolates users from the internal technical details and is convenient to use. The project is released on Github.
Anthology ID:
2021.acl-demo.12
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
99–106
Language:
URL:
https://aclanthology.org/2021.acl-demo.12
DOI:
10.18653/v1/2021.acl-demo.12
Bibkey:
Cite (ACL):
Zhichao Geng, Hang Yan, Xipeng Qiu, and Xuanjing Huang. 2021. fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 99–106, Online. Association for Computational Linguistics.
Cite (Informal):
fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP (Geng et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-demo.12.pdf
Video:
 https://aclanthology.org/2021.acl-demo.12.mp4
Code
 fastnlp/fastHan