Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings

doi:arXiv:2107.02416

	Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
	Wang, Xinyu1 ; Jia, Zixia1 ; Jiang, Yong 2; Tu, Kewei1
	2021-07-06
状态	已发表
摘要	This paper describes the system used in submission from SHANGHAITECH team to the IWPT 2021 Shared Task. Our system is a graph-based parser with the technique of Automated Concatenation of Embeddings (ACE). Because recent work found that better word representations can be obtained by concatenating different types of embeddings, we use ACE to automatically find the better concatenation of embeddings for the task of enhanced universal dependencies. According to official results averaged on 17 languages, our system ranks 2nd over 9 teams.
DOI	arXiv:2107.02416
相关网址	查看原文
出处	Arxiv
WOS记录号	PPRN:11837353
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348431
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_屠可伟组
作者单位	1.ShanghaiTech Univ, Shanghai Engn Res Ctr Intelligent Vis & Imaging, Sch Informat Sci & Technol, Shanghai, Peoples R China 2.Alibaba Grp, DAMO Acad, Hangzhou, Peoples R China
推荐引用方式 GB/T 7714	Wang, Xinyu,Jia, Zixia,Jiang, Yong,et al. Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings. 2021.