ShanghaiTech University Knowledge Management System
Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training | |
2020-12 | |
会议录名称 | THE 1ST CONFERENCE OF THE ASIA-PACIFIC CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 10TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (AACL-IJCNLP 2020) |
发表状态 | 正式接收 |
DOI | / |
摘要 | In this paper, we propose second-order graphbased neural dependency parsing using message passing and end-to-end neural networks. We empirically show that our approaches match the accuracy of very recent state-ofthe-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing. We also empirically show the advantage of second-order parsing over first-order parsing and observe that the usefulness of the head-selection structured constraint vanishes when using BERT embedding. |
会议名称 | the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2020) |
收录类别 | CPCI ; CPCI-S |
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/124047 |
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 | Tu, Kewei |
作者单位 | 1.School of Information Science and Technology, ShanghaiTech University 2.Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences 3.University of Chinese Academy of Sciences 4.Shanghai Engineering Research Center of Intelligent Vision and Imaging |
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,Tu, Kewei. Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training[C],2020. |
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 |
[Tu, Kewei]的文章 |
百度学术 |
百度学术中相似的文章 |
[Wang, Xinyu]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 |
[Tu, Kewei]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
修改评论
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。