Unsupervised cross-lingual adaptation of dependency parsers using CRF autoencoders
2020
会议录名称FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS FINDINGS OF ACL: EMNLP 2020
卷号Findings of the Association for Computational Linguistics: EMNLP 2020
页码2127-2133
发表状态已发表
DOI/
摘要

We consider the task of cross-lingual adaptation of dependency parsers without annotated target corpora and parallel corpora. Previous work either directly applies a discriminative source parser to the target language, ignoring unannotated target corpora, or employs an unsupervised generative parser that can leverage unannotated target data but has weaker representational power than discriminative parsers. In this paper, we propose to utilize unsupervised discriminative parsers based on the CRF autoencoder framework for this task. We train a source parser and use it to initialize and regularize a target parser that is trained on unannotated target data. We conduct experiments that transfer an English parser to 20 target languages. The results show that our method significantly outperforms previous methods. ©2020 Association for Computational Linguistics

关键词Computational linguistics Auto encoders Cross-lingual Dependency parser English parser Parallel corpora Power Target language
会议名称Findings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020
出版地209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
会议地点Virtual, Online
会议日期November 16, 2020 - November 20, 2020
URL查看原文
收录类别EI ; CPCI-S
语种英语
资助项目National Natural Science Foundation of China[61976139]
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号WOS:001181866501016
出版者Association for Computational Linguistics (ACL)
EI入藏号20214511115928
EI主题词Learning systems
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/251840
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
作者单位
School of Information Science and Technology, ShanghaiTech University Shanghai Engineering, Research Center of Intelligent Vision and Imaging, 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
Li, Zhao,Tu, Kewei. Unsupervised cross-lingual adaptation of dependency parsers using CRF autoencoders[C]. 209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA:Association for Computational Linguistics (ACL),2020:2127-2133.
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
[Li, Zhao]的文章
[Tu, Kewei]的文章
百度学术
百度学术中相似的文章
[Li, Zhao]的文章
[Tu, Kewei]的文章
必应学术
必应学术中相似的文章
[Li, Zhao]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。