Knowledge Commons of Institute of Automation,CAS
A Graph-to-Sequence Learning Framework for Summarizing Opinionated Texts | |
Wei, Penghui1,2; Zhao, Jiahao1,2; Mao, Wenji1,2 | |
发表期刊 | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING |
ISSN | 2329-9290 |
2021 | |
卷号 | 29期号:1页码:1650-1660 |
摘要 | There is a great need for effective summarization methods to absorb the key points of large amounts of opinions expressed on the Web. In this paper, we study the problem of opinionated text summarization, which aims to generate a coherent summary for a set of opinionated texts towards a specific topic (e.g., a movie or a controversial issue). The main characteristic of this problem is that the input set contains an arbitrary number of texts, which brings about redundant opinions and useless texts. Further, informative opinions to be summarized are scattered over different opinionated texts, thus it is vital to avoid focusing only on partial opinions. However, previous work can not tackle the above two issues effectively. To address such issues, we propose a two-stage graph-to-sequence learning framework for summarizing opinionated texts. The first stage selects summary-worthy texts from all input opinionated texts, and we construct an opinion relation graph to help estimate salience via exploiting the relationships among the input texts. Given the selected texts, the second stage generates an opinion summary via a maximal marginal relevance guided graph-to-sequence model, which gives consideration to both salient and non-redundant opinions. Experimental results on two benchmark datasets show that our framework outperforms the existing state-of-the-art methods. Human evaluation further verifies that our framework can generate more informative and compact opinion summaries than previous methods. |
关键词 | Opinionated text summarization |
DOI | 10.1109/TASLP.2021.3071667 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | NSFC[11832001] ; NSFC[71621002] ; Ministry of Science and Technology of China[2020AAA0108401] ; Ministry of Science and Technology of China[2020AAA0108405] ; Beijing Nova Program[Z201100006820085] ; Beijing Municipal Science and Technology Commission |
项目资助者 | NSFC ; Ministry of Science and Technology of China ; Beijing Nova Program ; Beijing Municipal Science and Technology Commission |
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/173211/44658 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
通讯作者 | Mao, Wenji |
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 | Wei, Penghui,Zhao, Jiahao,Mao, Wenji. A Graph-to-Sequence Learning Framework for Summarizing Opinionated Texts[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2021,29(1):1650-1660. |
APA | Wei, Penghui,Zhao, Jiahao,&Mao, Wenji.(2021).A Graph-to-Sequence Learning Framework for Summarizing Opinionated Texts.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,29(1),1650-1660. |
MLA | Wei, Penghui,et al."A Graph-to-Sequence Learning Framework for Summarizing Opinionated Texts".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 29.1(2021):1650-1660. |
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 | ||
[2021TASLP] A Graph-(1818KB) | 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