Abstract
Definition generation, which aims to automatically generate dictionary definitions for words, has recently been proposed to assist the construction of dictionaries and help people understand unfamiliar texts. However, previous works hardly consider explicitly modeling the “components” of definitions, leading to under-specific generation results. In this paper, we propose ESD, namely Explicit Semantic Decomposition for definition Generation, which explicitly decomposes the meaning of words into semantic components, and models them with discrete latent variables for definition generation. Experimental results show that achieves top results on WordNet and Oxford benchmarks, outperforming strong previous baselines.- Anthology ID:
- 2020.acl-main.65
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 708–717
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.65
- DOI:
- 10.18653/v1/2020.acl-main.65
- Cite (ACL):
- Jiahuan Li, Yu Bao, Shujian Huang, Xinyu Dai, and Jiajun Chen. 2020. Explicit Semantic Decomposition for Definition Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 708–717, Online. Association for Computational Linguistics.
- Cite (Informal):
- Explicit Semantic Decomposition for Definition Generation (Li et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.acl-main.65.pdf