Combining generative and discriminative approaches to unsupervised dependency parsing via dual decomposition
2017
会议录名称2017 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2017
页码1689-1694
发表状态已发表
摘要Unsupervised dependency parsing aims to learn a dependency parser from unannotated sentences. Existing work focuses on either learning generative models using the expectation-maximization algorithm and its variants, or learning discriminative models using the discriminative clustering algorithm. In this paper, we propose a new learning strategy that learns a generative model and a discriminative model jointly based on the dual decomposition method. Our method is simple and general, yet effective to capture the advantages of both models and improve their learning results. We tested our method on the UD treebank and achieved a state-of-the-art performance on thirty languages.
© 2017 Association for Computational Linguistics.
会议地点Copenhagen, Denmark
收录类别EI
资助项目National Natural Science Foundation of China[61503248]
出版者Association for Computational Linguistics (ACL)
EI入藏号20194207538745
EI主题词Clustering algorithms ; Image segmentation ; Maximum principle ; Natural language processing systems ; Syntactics
EI分类号Data Processing and Image Processing:723.2 ; Information Sources and Analysis:903.1
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/29234
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
School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一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
Jiang, Yong,Han, Wenjuan,Tu, Kewei. Combining generative and discriminative approaches to unsupervised dependency parsing via dual decomposition[C]:Association for Computational Linguistics (ACL),2017:1689-1694.
条目包含的文件 下载所有文件
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
[Jiang, Yong]的文章
[Han, Wenjuan]的文章
[Tu, Kewei]的文章
百度学术
百度学术中相似的文章
[Jiang, Yong]的文章
[Han, Wenjuan]的文章
[Tu, Kewei]的文章
必应学术
必应学术中相似的文章
[Jiang, Yong]的文章
[Han, Wenjuan]的文章
[Tu, Kewei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 10.18653@v1@D17-1177.pdf
格式: Adobe PDF
文件名: 10.18653@v1@D17-1177.pdf
格式: Adobe PDF
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。