Multilingual summarization with polytope model

Natalia Vanetik, Marina Litvak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

The problem of extractive text summarization for a collection of documents is defined as the problem of selecting a small subset of sentences so that the contents and meaning of the original document set are preserved in the best possible way. In this paper we describe the linear programming-based global optimization model to rank and extract the most relevant sentences to a summary. We introduce three different objective functions being optimized. These functions define a relevance of a sentence that is being maximized, in different manners, such as: coverage of meaningful words of a document, coverage of its bigrams, or coverage of frequent sequences of words. We supply here an overview of our system's participation in the MultiLing contest of SIGDial 2015.

Original languageEnglish
Title of host publicationSIGDIAL 2015 - 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages227-231
Number of pages5
ISBN (Electronic)9781941643754
DOIs
StatePublished - 1 Jan 2015
Externally publishedYes
Event16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2015 - Prague, Czech Republic
Duration: 2 Sep 20154 Sep 2015

Publication series

NameSIGDIAL 2015 - 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference

Conference

Conference16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2015
Country/TerritoryCzech Republic
CityPrague
Period2/09/154/09/15

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Modeling and Simulation
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Multilingual summarization with polytope model'. Together they form a unique fingerprint.

Cite this