CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Event co-reference resolution via a multi-loss neural network without using argument information
Zuo, Xinyu1,2; Chen, Yubo1; Liu, Kang1,2; Zhao, Jun1,2
Source PublicationSCIENCE CHINA-INFORMATION SCIENCES
ISSN1674-733X
2019-11-01
Volume62Issue:11Pages:9
Corresponding AuthorChen, Yubo(yubo.chen@nlpr.ia.ac.cn) ; Liu, Kang(kliu@nlpr.ia.ac.cn)
AbstractEvent co-reference resolution is an important task in natural language processing, and nearly all the existing approaches for this task rely on event argument information. However, these methods tend to suffer from error propagation from event argument extraction. Additionally, not every event mention contains all arguments of an event, and the argument information may confuse the model where events contain arguments to detect an event co-reference in real text. Furthermore, the context information of an event is useful to infer the co-reference between events. Thus, to reduce the errors propagated from event argument extraction and use context information effectively, we propose a multi-loss neural network model that does not require any argument information relating to the within-document event co-reference resolution task; furthermore, it achieves a significantly better performance than the state-of-the-art methods.
Keywordevent co-reference resolution neural network information extraction multi-loss function event extraction
DOI10.1007/s11432-018-9833-1
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61533018] ; National Natural Science Foundation of China[61806201] ; National Natural Science Foundation of China[61702512] ; Independent Research Project of National Laboratory of Pattern Recognition ; CCF-Tencent Open Fund
Funding OrganizationNational Natural Science Foundation of China ; Independent Research Project of National Laboratory of Pattern Recognition ; CCF-Tencent Open Fund
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic
WOS IDWOS:000490155800001
PublisherSCIENCE PRESS
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26130
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorChen, Yubo; Liu, Kang
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zuo, Xinyu,Chen, Yubo,Liu, Kang,et al. Event co-reference resolution via a multi-loss neural network without using argument information[J]. SCIENCE CHINA-INFORMATION SCIENCES,2019,62(11):9.
APA Zuo, Xinyu,Chen, Yubo,Liu, Kang,&Zhao, Jun.(2019).Event co-reference resolution via a multi-loss neural network without using argument information.SCIENCE CHINA-INFORMATION SCIENCES,62(11),9.
MLA Zuo, Xinyu,et al."Event co-reference resolution via a multi-loss neural network without using argument information".SCIENCE CHINA-INFORMATION SCIENCES 62.11(2019):9.
Files in This Item: Download All
File Name/Size DocType Version Access License
zuoxinyu.pdf(360KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zuo, Xinyu]'s Articles
[Chen, Yubo]'s Articles
[Liu, Kang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zuo, Xinyu]'s Articles
[Chen, Yubo]'s Articles
[Liu, Kang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zuo, Xinyu]'s Articles
[Chen, Yubo]'s Articles
[Liu, Kang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: zuoxinyu.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.