典型文献
Exploiting comments information to improve legal public opinion news abstractive summarization
文献摘要：
Automatically generating a brief summary for legal-related public opinion news(LPO-news,which contains legal words or phrases)plays an important role in rapid and effective public opinion disposal.For LPO-news,the critical case elements which are significant parts of the summary may be mentioned several times in the reader comments.Conse-quently,we investigate the task of comment-aware abstractive text summarization for LPO-news,which can generate salient summary by learning pivotal case elements from the reader comments.In this paper,we present a hierarchical comment-aware encoder(HCAE),which contains four components:1)a traditional sequenceto-sequence framework as our baseline;2)a selective denoising module to filter the noisy of comments and distinguish the case elements;3)a merge module by coupling the source article and comments to yield comment-aware context representation;4)a recoding module to capture the interaction among the source article words conditioned on the comments.Extensive experiments are conducted on a large dataset of legal public opinion news collected from micro-blog,and results show that the proposed model outperforms several existing state-of-the-art baseline models under the ROUGE metrics.
文献关键词：
中图分类号：
作者姓名：
Yuxin HUANG;Zhengtao YU;Yan XIANG;Zhiqiang YU;Junjun GUO
作者机构：
Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500,China
文献出处：
引用格式：
[1]Yuxin HUANG;Zhengtao YU;Yan XIANG;Zhiqiang YU;Junjun GUO-.Exploiting comments information to improve legal public opinion news abstractive summarization)[J].计算机科学前沿,2022(06):29-38
A类：
abstractive,HCAE,sequenceto,recoding
B类：
Exploiting,comments,information,improve,legal,public,opinion,news,summarization,Automatically,generating,brief,summary,related,LPO,which,contains,words,phrases,plays,important,role,rapid,effective,disposal,For,critical,case,elements,significant,parts,may,be,mentioned,several,times,reader,Conse,quently,we,investigate,task,aware,generate,salient,by,learning,pivotal,from,In,this,paper,hierarchical,encoder,four,components,traditional,framework,baseline,selective,denoising,module,filter,noisy,distinguish,merge,coupling,source,article,yield,context,representation,capture,interaction,among,conditioned,Extensive,experiments,conducted,large,dataset,collected,micro,blog,results,show,that,proposed,outperforms,existing,state,models,under,ROUGE,metrics
AB值：
0.518903
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
