Abstract

We present a fuzzy-theory based approach to coreference resolution and its application to text summarization.

Automatic determination of coreference between noun phrases is fraught with uncertainty. We show how fuzzy sets can be used to design a new coreference algorithm which captures this uncertainty in an explicit way and allows us to define varying degrees of coreference.

The algorithm is evaluated within a system that participated in the 10-word summary task of the DUC 2003 competition.

Reference

René Witte and Sabine Bergler. Fuzzy Coreference Resolution for Summarization. Proceedings of 2003 International Symposium on Reference Resolution and Its Applications to Question Answering and Summarization (ARQAS), pp. 43-50, June 23-24, 2003, Università Ca' Foscari, Venice, Italy.

Bibtex entry (also for download):

@InProceedings{WiBe03,
  author =       {Ren{\'{e}} Witte and Sabine Bergler},
  title =        {{Fuzzy Coreference Resolution for Summarization}},
  booktitle =    {Proceedings of 2003 International Symposium on 
                  Reference Resolution and Its Applications to 
                  Question Answering and Summarization (ARQAS)},
  pages =        {43--50},
  year =         {2003},
  month =        {June 23--24},
  organization = {Universit{\`{a}} Ca' Foscari},
  address =      {Venice, Italy},
  note =         {\url{http://rene-witte.net}}
}

You can also visit the conference website.

Download

URL: wittebergler_fuzzycoref.pdf.
MD5 checksum: c9f14601f3333b46873190e4eb2ff896

You can also download our slides from the Venice talk.
MD5 checksum: c35c01929aa84e21e331a0e2d4c58d50

Copyright © 2003 René Witte and Sabine Bergler. All rights reserved.