Joint Optimization of User-desired Content in Multi-document Summaries by Learning from User Feedback

被引：17

作者：

Avinesh, P. V. S. ^{[1
]}

Meyer, Christian M.

机构：

[1] Tech Univ Darmstadt, Res Training Grp AIPHES, Darmstadt, Germany

来源：

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1 | 2017年

关键词：

D O I：

10.18653/v1/P17-1124

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper, we propose an extractive multi-document summarization (MDS) system using joint optimization and active learning for content selection grounded in user feedback. Our method interactively obtains user feedback to gradually improve the results of a state-of-the-art integer linear programming (ILP) framework for MDS. Our methods complement fully automatic methods in producing high-quality summaries with a minimum number of iterations and feedbacks. We conduct multiple simulation-based experiments and analyze the effect of feedback-based concept selection in the ILP setup in order to maximize the user-desired content in the summary.

引用

页码：1353 / 1363

页数：11

共 37 条

[1]

[Anonymous], 2016, 12 C ASS MACHINE TRA

[2]

[Anonymous], 2012, P COLING 2012

[3]

[Anonymous], 2012, P 13 C EUROPEAN CHAP

[4]

[Anonymous], 2009, Proceedings of the Workshop on Integer Linear Programming for Natural Langauge Processing

[5]

[Anonymous], 2012, Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

[6]

Benikova Darina, 2016, P 26 INT C COMP LING, P1039

[7]

Berkovsky S, 2008, LECT NOTES COMPUT SC, V5149, P267

[8]

Boudin F., 2015, C EMP METH NAT LANG, P1914, DOI DOI 10.18653/V1/D15-1220

[9]

Cao ZQ, 2016, AAAI CONF ARTIF INTE, P2906

[10]

Craven TC, 2000, J AM SOC INFORM SCI, V51, P745, DOI 10.1002/(SICI)1097-4571(2000)51:8<745::AID-ASI70>3.0.CO

← 1 2 3 4 →