Using Knowledge-poor Coreference Resolution for Text Summarization


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.


Workshop on Text Summarization, Document Understanding Conference (DUC), May 31-June 1, 2003, Edmonton, Canada. NIST.

Bibtex entry (also for download):

  author =       {Sabine Bergler and Ren{\'{e}} Witte
and Michelle Khalife and Zhuoyan Li and Frank Rudzicz},
  title =        {{Using Knowledge-poor Coreference Resolution 
                  for Text Summarization}},
  booktitle =    {Workshop on Text Summarization},
  year =         {2003},
  series =       {Document Understanding Conference (DUC)},
  address =      {Edmonton, Canada},
  month =        {May 31--June 1},
  organization = {NIST},
  note =         {\url{}},
  annote =       {Workshop at HLT-NAACL 2003}

You can also visit the DUC homepage at NIST.


URL: Also available: local copy.
MD5 checksum: e7d7d25f79cb1e64cf2d575ba9d70f12
Copyright © 2003 Sabine Bergler, René Witte, Michelle Khalife, Zhuoyan Li, and Frank Rudzicz. All rights reserved.