CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization
Li, Haoran1,2; Zhu, Junnan1,2; Zhang, Jiajun1,2; Zong, Chengqing1,2,3
2019
Conference NameProceedings of the 27th International Conference on Computational Linguistics
Conference Date2018, 8,20-26
Conference PlaceSanta Fe, New Mexico, USA
Abstract

In this paper, we investigate the sentence summarization task that produces a summary from a source sentence. Neural sequence-to-sequence models have gained considerable success for this task, while most existing approaches only focus on improving word overlap between the generated summary and the reference, which ignore the correctness, i.e., the summary should not contain error messages with respect to the source sentence. We argue that correctness is an essential requirement for summarization systems. Considering a correct summary is semantically entailed by the source sentence, we incorporate entailment knowledge into abstractive summarization models. We propose an entailment-aware encoder under multi-task framework (i.e., summarization generation and entailment recognition) and an entailment-aware decoder by entailment Reward Augmented Maximum Likelihood (RAML) training. Experimental results demonstrate that our models significantly outperform baselines from the aspects of informativeness and correctness.

Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23109
Collection模式识别国家重点实验室_自然语言处理
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.CAS Center for Excellence in Brain Science and Intelligence Technology
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Li, Haoran,Zhu, Junnan,Zhang, Jiajun,et al. Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
5COLING.pdf(287KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Haoran]'s Articles
[Zhu, Junnan]'s Articles
[Zhang, Jiajun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Haoran]'s Articles
[Zhu, Junnan]'s Articles
[Zhang, Jiajun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Haoran]'s Articles
[Zhu, Junnan]'s Articles
[Zhang, Jiajun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 5COLING.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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