Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction
Penghui Wei1,2; Jiahao Zhao1,2; Wenji Mao1,2
2020-07
会议名称The 58th Annual Meeting of the Association for Computational Linguistics
会议日期2020-7
会议地点Online
出版者ACL
摘要

Emotion-cause pair extraction aims to extract all emotion clauses coupled with their cause clauses from a given document. Previous work employs two-step approaches, in which the first step extracts emotion clauses and cause clauses separately, and the second step trains a classifier to filter out negative pairs. However, such pipeline-style system for emotion-cause pair extraction is suboptimal because it suffers from error propagation and the two steps may not adapt to each other well. In this paper, we tackle emotion-cause pair extraction from a ranking perspective, i.e., ranking clause pair candidates in a document, and propose a one-step neural approach which emphasizes inter-clause modeling to perform end-to-end extraction. It models the interrelations between the clauses in a document to learn clause representations with graph attention, and enhances clause pair representations with kernel-based relative position embedding for effective ranking. Experimental results show that our approach significantly outperforms the current two-step systems, especially in the condition of extracting multiple pairs in one document.

收录类别EI
语种英语
七大方向——子方向分类自然语言处理
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/44760
专题复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
通讯作者Wenji Mao
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
Penghui Wei,Jiahao Zhao,Wenji Mao. Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction[C]:ACL,2020.
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
[2020ACL] Effective (4038KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Penghui Wei]的文章
[Jiahao Zhao]的文章
[Wenji Mao]的文章
百度学术
百度学术中相似的文章
[Penghui Wei]的文章
[Jiahao Zhao]的文章
[Wenji Mao]的文章
必应学术
必应学术中相似的文章
[Penghui Wei]的文章
[Jiahao Zhao]的文章
[Wenji Mao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: [2020ACL] Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction.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。