Knowledge-guided unsupervised rhetorical parsing for text summarization
Hou, Shengluan1,2; Lu, Ruqian1,3,4
AbstractAutomatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. However, there is still no guarantee that the generated summaries are grammatical, concise, and convey all salient information as the original documents have. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model, and domain knowledge concern for ATS. This architecture mainly contains three components: domain knowledge base construction based on representation learning, the attentional encoder-decoder model for rhetorical parsing, and subroutine-based model for text summarization. Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived. In the unsupervised rhetorical parsing module, the idea of translation was adopted to alleviate the problem of data scarcity. The subroutine-based summarization model purely depends on the derived rhetorical structure trees and can generate content-balanced results. To evaluate the summary results without golden standard, we proposed an unsupervised evaluation metric, whose hyper-parameters were tuned by supervised learning. Experimental results show that, on a large-scale Chinese dataset, our proposed approach can obtain comparable performances compared with existing methods. (C) 2020 Elsevier Ltd. All rights reserved.
KeywordAutomatic text summarization Rhetorical structure theory Domain knowledge base Attentional encoder-decoder Natural language processing
Indexed BySCI
Funding ProjectNational Key Research and Development Program of China[2016YFB1000902] ; National Natural Science Foundation of China[61232015] ; National Natural Science Foundation of China[61472412] ; National Natural Science Foundation of China[61621003]
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000567083300010
Citation statistics
Document Type期刊论文
Corresponding AuthorHou, Shengluan
Affiliation1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Key Lab MADIS, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Hou, Shengluan,Lu, Ruqian. Knowledge-guided unsupervised rhetorical parsing for text summarization[J]. INFORMATION SYSTEMS,2020,94:12.
APA Hou, Shengluan,&Lu, Ruqian.(2020).Knowledge-guided unsupervised rhetorical parsing for text summarization.INFORMATION SYSTEMS,94,12.
MLA Hou, Shengluan,et al."Knowledge-guided unsupervised rhetorical parsing for text summarization".INFORMATION SYSTEMS 94(2020):12.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hou, Shengluan]'s Articles
[Lu, Ruqian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hou, Shengluan]'s Articles
[Lu, Ruqian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hou, Shengluan]'s Articles
[Lu, Ruqian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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