Skip navigation.
Home
Semantic Software Lab
Concordia University
Montréal, Canada

Using Knowledge-poor Coreference Resolution for Text Summarization

Printer-friendly versionPrinter-friendly versionPDF versionPDF version
Title{Using Knowledge-poor Coreference Resolution for Text Summarization}
Publication TypeConference Paper
Year of Publication2003
AuthorsBergler, S., R. Witte, M. Khalife, Z. Li, and F. Rudzicz
Refereed DesignationNon-Refereed
Conference NameWorkshop on Text Summarization
Tertiary TitleDocument Understanding Conference (DUC)
Date PublishedMay 31–June 1
PublisherNIST
Conference LocationEdmonton, Canada
Abstract

We present a system that produces 10-word summaries based on the single summarization strategy of outputting noun phrases representing the most important text entities (as represented by noun phrase coreference chains). The coreference chains were computed using fuzzy set theory combined with knowledge-poor corefernce heuristics.

URLhttp://www-nlpir.nist.gov/projects/duc/pubs/2003final.papers/concordia.final.pdf
Copyright

Copyright © 2003 Sabine Bergler, René Witte, Michelle Khalife, Zhuoyan Li, and Frank Rudzicz. All rights reserved.

AttachmentSize
concordia.final_.pdf118.77 KB