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, Haoran; Zhu, Junnan; Zhang, Jiajun; Zong, Chengqing
2018
会议名称COLING
会议日期2018-8
会议地点USA
摘要

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.

文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23206
专题模式识别国家重点实验室_自然语言处理
作者单位中国科学院自动化研究所
第一作者单位中国科学院自动化研究所
推荐引用方式
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],2018.
条目包含的文件
条目无相关文件。
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
[Li, Haoran]的文章
[Zhu, Junnan]的文章
[Zhang, Jiajun]的文章
百度学术
百度学术中相似的文章
[Li, Haoran]的文章
[Zhu, Junnan]的文章
[Zhang, Jiajun]的文章
必应学术
必应学术中相似的文章
[Li, Haoran]的文章
[Zhu, Junnan]的文章
[Zhang, Jiajun]的文章
相关权益政策
暂无数据
收藏/分享
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。