Peyrard, Maxime ; Eckle-Kohler, Judith (2016)
Optimizing an Approximation of ROUGE - a Problem-Reduction Approach to Extractive Multi-Document Summarization.
54th Annual Meeting of the Association for Computational Linguistics (ACL 2016). Berlin, Germany (07.08.2016-12.08.2016)
doi: 10.18653/v1/P16-1172
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2016 |
| Autor(en): | Peyrard, Maxime ; Eckle-Kohler, Judith |
| Art des Eintrags: | Bibliographie |
| Titel: | Optimizing an Approximation of ROUGE - a Problem-Reduction Approach to Extractive Multi-Document Summarization |
| Sprache: | Englisch |
| Publikationsjahr: | August 2016 |
| Ort: | Berlin |
| Verlag: | Association for Computational Linguistics |
| Buchtitel: | Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016) |
| Band einer Reihe: | Volume 1: Long Papers |
| Veranstaltungstitel: | 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016) |
| Veranstaltungsort: | Berlin, Germany |
| Veranstaltungsdatum: | 07.08.2016-12.08.2016 |
| DOI: | 10.18653/v1/P16-1172 |
| URL / URN: | http://www.aclweb.org/anthology/P16-1172 |
| Zugehörige Links: | |
| Kurzbeschreibung (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. |
| Freie Schlagworte: | UKP_reviewed;AIPHES_area_b2 |
| ID-Nummer: | TUD-CS-2016-0108 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 30 Dez 2016 17:45 |
| Letzte Änderung: | 02 Jul 2024 09:37 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum