Inspired by this process, we propose to enhance DG with word formation features.
#DECOMPOSE DEFINITION MODS#
Cite (Informal): Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation (Zheng et al., NAACL 2021) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: = "Decompose, Fuse and Generate: A Formation-Informed Method for, flower) using a formation rule (Modifier-Head). Association for Computational Linguistics.
In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5524–5531, Online. Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation. 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: DOI: 10.18653/v1/2021.naacl-main.437 Bibkey: zheng-etal-2021-decompose Cite (ACL): Hua Zheng, Damai Dai, Lei Li, Tianyu Liu, Zhifang Sui, Baobao Chang, and Yang Liu. Experimental results show that our method is both effective and robust. 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. 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). Most existing methods take the source word as an indecomposable semantic unit. Abstract In this paper, we tackle the task of Definition Generation (DG) in Chinese, which aims at automatically generating a definition for a word.
0 kommentar(er)
