Adapting unsupervised syntactic parsing methodology for discourse dependency parsing
2021-07-01
会议录名称ACL-IJCNLP 2021 - 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, PROCEEDINGS OF THE CONFERENCE
页码5782-5794
发表状态已发表
摘要

One of the main bottlenecks in developing discourse dependency parsers is the lack of annotated training data. A potential solution is to utilize abundant unlabeled data by using unsupervised techniques, but there is so far little research in unsupervised discourse dependency parsing. Fortunately, unsupervised syntactic dependency parsing has been studied for decades, which could potentially be adapted for discourse parsing. In this paper, we propose a simple yet effective method to adapt unsupervised syntactic dependency parsing methodology for unsupervised discourse dependency parsing. We apply the method to adapt two state-of-the-art unsupervised syntactic dependency parsing methods. Experimental results demonstrate that our adaptation is effective. Moreover, we extend the adapted methods to the semi-supervised and supervised setting and surprisingly, we find that they outperform previous methods specially designed for supervised discourse parsing. Further analysis shows our adaptations result in superiority not only in parsing accuracy but also in time and space efficiency. © 2021 Association for Computational Linguistics

会议录编者/会议主办者Amazon Science ; Apple ; Bloomberg Engineering ; et al. ; Facebook AI ; Google Research
关键词Computational linguistics Annotated training data Dependency parser Dependency parsing Discourse parsing Simple++ Syntactic dependencies Syntactic parsing Two state Unlabeled data Unsupervised techniques
会议名称Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
会议地点Virtual, Online
会议日期August 1, 2021 - August 6, 2021
收录类别EI
语种英语
出版者Association for Computational Linguistics (ACL)
EI入藏号20214611160399
EI主题词Syntactics
EI分类号721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory
原始文献类型Conference article (CA)
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/133491
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
通讯作者Tu, Kewei
作者单位
1.School of Information Science and Technology, ShanghaiTech University, China;
2.Shanghai Engineering Research Center of Intelligent Vision and Imaging, China;
3.Shanghai Institute of Microsystem and Information Technology, China;
4.University of Chinese Academy of Sciences, China;
5.Beijing Institute for General Artificial Intelligence, Beijing, 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
Zhang, Liwen,Wang, Ge,Han, Wenjuan,et al. Adapting unsupervised syntactic parsing methodology for discourse dependency parsing[C]//Amazon Science, Apple, Bloomberg Engineering, et al., Facebook AI, Google Research:Association for Computational Linguistics (ACL),2021:5782-5794.
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
[Zhang, Liwen]的文章
[Wang, Ge]的文章
[Han, Wenjuan]的文章
百度学术
百度学术中相似的文章
[Zhang, Liwen]的文章
[Wang, Ge]的文章
[Han, Wenjuan]的文章
必应学术
必应学术中相似的文章
[Zhang, Liwen]的文章
[Wang, Ge]的文章
[Han, Wenjuan]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。