Enumeration of extractive oracle summaries

Tsutomu Hirao, Masaaki Nishino, Jun Suzuki, Masaaki Nagata

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

To analyze the limitations and the future directions of the extractive summarization paradigm, this paper proposes an Integer Linear Programming (ILP) formulation to obtain extractive oracle summaries in terms of ROUGEn. We also propose an algorithm that enumerates all of the oracle summaries for a set of reference summaries to exploit F-measures that evaluate which system summaries contain how many sentences that are extracted as an oracle summary. Our experimental results obtained from Document Understanding Conference (DUC) corpora demonstrated the following: (1) room still exists to improve the performance of extractive summarization; (2) the F-measures derived from the enumerated oracle summaries have significantly stronger correlations with human judgment than those derived from single oracle summaries.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages386-396
Number of pages11
ISBN (Electronic)9781510838604
DOIs
Publication statusPublished - 2017
Event15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain
Duration: 2017 Apr 3 → 2017 Apr 7

Publication series

Name15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
Volume1

Other

Other15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
CountrySpain
CityValencia
Period17/4/3 → 17/4/7

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics

Access to Document

Fingerprint Dive into the research topics of 'Enumeration of extractive oracle summaries'. Together they form a unique fingerprint.

Cite this