TU Darmstadt / ULB / TUbiblio

Optimizing an Approximation of ROUGE - a Problem-Reduction Approach to Extractive Multi-Document Summarization

Peyrard, Maxime and Eckle-Kohler, Judith (2016):
Optimizing an Approximation of ROUGE - a Problem-Reduction Approach to Extractive Multi-Document Summarization.
In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), Association for Computational Linguistics, Berlin, Germany, August 2016, Volume 1: Long Papers, DOI: 10.18653/v1/P16-1172,
[Online-Edition: http://www.aclweb.org/anthology/P16-1172],
[Conference or Workshop Item]

Abstract

This paper presents a problem-reduction approach to extractive multi-document summarization: we propose a reduction to the problem of scoring individual sentences with their ROUGE scores based on supervised learning. For the summarization, we solve an optimization problem where the ROUGE score of the selected summary sentences is maximized. To this end, we derive an approximation of the ROUGE-N score of a set of sentences, and define a principled discrete optimization problem for sentence selection. Mathematical and empirical evidence suggests that the sentence selection step is solved almost exactly, thus reducing the problem to the sentence scoring task. We perform a detailed experimental evaluation on two DUC datasets to demonstrate the validity of our approach.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Peyrard, Maxime and Eckle-Kohler, Judith
Title: Optimizing an Approximation of ROUGE - a Problem-Reduction Approach to Extractive Multi-Document Summarization
Language: English
Abstract:

This paper presents a problem-reduction approach to extractive multi-document summarization: we propose a reduction to the problem of scoring individual sentences with their ROUGE scores based on supervised learning. For the summarization, we solve an optimization problem where the ROUGE score of the selected summary sentences is maximized. To this end, we derive an approximation of the ROUGE-N score of a set of sentences, and define a principled discrete optimization problem for sentence selection. Mathematical and empirical evidence suggests that the sentence selection step is solved almost exactly, thus reducing the problem to the sentence scoring task. We perform a detailed experimental evaluation on two DUC datasets to demonstrate the validity of our approach.

Title of Book: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016)
Volume: Volume 1: Long Papers
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_reviewed;AIPHES_area_b2
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Event Location: Berlin, Germany
Event Dates: August 2016
Date Deposited: 30 Dec 2016 17:45
DOI: 10.18653/v1/P16-1172
Official URL: http://www.aclweb.org/anthology/P16-1172
Identification Number: TUD-CS-2016-0108
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item