Knowledge Commons of Institute of Automation,CAS
Event Co-reference Resolution via a Multi-loss Neural Network without Using Argument Information | |
Xinyu Zuo1,2; Yubo Chen1,2; Kang Liu1,2; Jun Zhao1,2 | |
发表期刊 | Science China Information Sciences |
ISSN | 1674-733X |
2019 | |
卷号 | 62期号:11页码:212101:1–212101:9 |
摘要 | Event 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. |
关键词 | Event co-reference resolution Neural network Information extraction Multi-loss function Event extraction |
学科领域 | 计算机科学技术 ; 人工智能 ; 自然语言处理 |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1007/s11432-018-9833-1 |
URL | 查看原文 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Independent Research Project of National Laboratory of Pattern Recognition ; National Natural Science Foundation of China[61702512] ; National Natural Science Foundation of China[61806201] ; National Natural Science Foundation of China[61533018] ; CCF-Tencent Open Fund |
七大方向——子方向分类 | 自然语言处理 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44828 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Yubo Chen; Kang Liu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Xinyu Zuo,Yubo Chen,Kang Liu,et al. Event Co-reference Resolution via a Multi-loss Neural Network without Using Argument Information[J]. Science China Information Sciences,2019,62(11):212101:1–212101:9. |
APA | Xinyu Zuo,Yubo Chen,Kang Liu,&Jun Zhao.(2019).Event Co-reference Resolution via a Multi-loss Neural Network without Using Argument Information.Science China Information Sciences,62(11),212101:1–212101:9. |
MLA | Xinyu Zuo,et al."Event Co-reference Resolution via a Multi-loss Neural Network without Using Argument Information".Science China Information Sciences 62.11(2019):212101:1–212101:9. |
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 | ||
212101.pdf(360KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论