版权说明 操作指南
首页 > 成果 > 详情

Main Point Generator: Summarizing with a Focus

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
会议论文
作者:
Chung, Tong Lee*;Xu, Bin;Liu, Yongbin*;Ouyang, Chunping
通讯作者:
Chung, Tong Lee;Liu, Yongbin
作者机构:
[Xu, Bin; Chung, Tong Lee] Tsinghua Univ, Dept Comp Sci & Technol, Beijing, Peoples R China.
[Xu, Bin; Chung, Tong Lee] Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China.
[Ouyang, Chunping; Liu, Yongbin] Univ South China, Coll Comp, Hengyang, Peoples R China.
通讯机构:
[Chung, Tong Lee] T
[Chung, Tong Lee] B
[Liu, Yongbin] U
Tsinghua Univ, Dept Comp Sci & Technol, Beijing, Peoples R China.
Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China.
语种:
英文
关键词:
Text summarization;Sequence-to-sequence;Pointer;Coverage
期刊:
Lecture Notes in Computer Science
ISSN:
0302-9743
年:
2018
卷:
10827
页码:
924-932
会议名称:
23rd International Conference on Database Systems for Advanced Applications (DASFAA).
会议论文集名称:
Lecture Notes in Computer Science
会议时间:
MAY 21-24, 2018
会议地点:
Gold Coast, AUSTRALIA
会议主办单位:
[Chung, Tong Lee;Xu, Bin] Tsinghua Univ, Dept Comp Sci & Technol, Beijing, Peoples R China.^[Chung, Tong Lee;Xu, Bin] Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China.^[Liu, Yongbin;Ouyang, Chunping] Univ South China, Coll Comp, Hengyang, Peoples R China.
主编:
Pei, J Manolopoulos, Y Sadiq, S Li, J
出版地:
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
出版者:
SPRINGER INTERNATIONAL PUBLISHING AG
ISBN:
978-3-319-91452-7; 978-3-319-91451-0
基金类别:
China National High-Tech Project (863) [2015AA015401]; Beijing Key Lab of Networked Multimedia; State Key Program of National Natural Science of ChinaNational Natural Science Foundation of China (NSFC) [61533018]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61402220]; Philosophy and Social Science Foundation of Hunan Province [16YBA323]
机构署名:
本校为通讯机构
院系归属:
计算机科学与技术学院
摘要:
Text summarization is attracting more and more attention while deep neural network has had many successful application in NLP. One problem of such models is its inability to focus on the essentials of documents, thus generating summaries that may not be important, especially during multi-sentence summarization. In this paper, we propose Main Pointer Generator (MPG) to address the problem, where at each decoder step the whole document is taken into consideration when calculating the probability of next generated token. We experiment with CNN/Daily news corpus and results show that summaries our...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com