Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
2020
会议录名称16TH INTERNATIONAL CONFERENCE ON PARSING TECHNOLOGIES AND IWPT 2020 SHARED TASK ON PARSING INTO ENHANCED UNIVERSAL DEPENDENCIES
页码215-220
发表状态已发表
摘要

This paper presents the system used in our submission to the IWPT 2020 Shared Task. Our system is a graph-based parser with second-order inference. For the low-resource Tamil corpus, we specially mixed the training data of Tamil with other languages and significantly improved the performance of Tamil. Due to our misunderstanding of the submission requirements, we submitted graphs that are not connected, which makes our system only rank 6th over 10 teams. However, after we fixed this problem, our system is 0.6 ELAS higher than the team that ranked 1st in the official results.

关键词Computational linguistics Dependency parsing Graph-based Performance Second orders Training data
会议名称16th International Conference on Parsing Technologies, IWPT 2020, co-located with the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
出版地209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
会议地点Virtual, Online, United states
会议日期July 9, 2020
收录类别CPCI ; ISSHP ; CPCI-S ; EI
语种英语
WOS研究方向Computer Science ; Linguistics
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Linguistics
WOS记录号WOS:000563425200022
出版者ASSOC COMPUTATIONAL LINGUISTICS-ACL
EI入藏号20214411097567
EI主题词Graphic methods
EI分类号721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory
原始文献类型Proceedings Paper
引用统计
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/123137
专题信息科学与技术学院_硕士生
信息科学与技术学院_PI研究组_屠可伟组
信息科学与技术学院_博士生
通讯作者Wang, Xinyu
作者单位
1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China
2.DAMO Acad, Alibaba Grp, Hangzhou, Peoples R China
第一作者单位信息科学与技术学院
通讯作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Wang, Xinyu,Jiang, Yong,Tu, Kewei. Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data[C]. 209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA:ASSOC COMPUTATIONAL LINGUISTICS-ACL,2020:215-220.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Wang, Xinyu]的文章
[Jiang, Yong]的文章
[Tu, Kewei]的文章
百度学术
百度学术中相似的文章
[Wang, Xinyu]的文章
[Jiang, Yong]的文章
[Tu, Kewei]的文章
必应学术
必应学术中相似的文章
[Wang, Xinyu]的文章
[Jiang, Yong]的文章
[Tu, Kewei]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。