Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation
Hua Zheng, Damai Dai, Lei Li, Tianyu Liu, Zhifang Sui, Baobao Chang, Yang Liu
Abstract
In this paper, we tackle the task of Definition Generation (DG) in Chinese, which aims at automatically generating a definition for a word. Most existing methods take the source word as an indecomposable semantic unit. However, in parataxis languages like Chinese, word meanings can be composed using the word formation process, where a word (“桃花”, peach-blossom) is formed by formation components (“桃”, peach; “花”, flower) using a formation rule (Modifier-Head). Inspired by this process, we propose to enhance DG with word formation features. We build a formation-informed dataset, and propose a model DeFT, which Decomposes words into formation features, dynamically Fuses different features through a gating mechanism, and generaTes word definitions. Experimental results show that our method is both effective and robust.- Anthology ID:
- 2021.naacl-main.437
- 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
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5524–5531
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.437
- DOI:
- 10.18653/v1/2021.naacl-main.437
- Cite (ACL):
- Hua Zheng, Damai Dai, Lei Li, Tianyu Liu, Zhifang Sui, Baobao Chang, and Yang Liu. 2021. Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5524–5531, Online. Association for Computational Linguistics.
- Cite (Informal):
- Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation (Zheng et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.437.pdf