@InProceedings{daume02noisy,
  author =       {Hal {Daum\'e III} and Daniel Marcu},
  title =        {A Noisy-Channel Model for Document Compression},
  booktitle =    {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL -- 2002)},
  year =         {2002},
  month =        {July 6 -- 12},
  address =      {Philadelphia, PA},
  pages =        {449 - 456},
  abstract =     {
    We present a document compression system that uses a hierarchical
    noisy-channel model of text production.  Our compression system
    first automatically derives the syntactic structure of each
    sentence and the overall discourse structure of the text given as
    input.  The system then uses a statistical hierarchical model of
    text production in order to drop non-important syntactic and
    discourse constituents so as to generate coherent, grammatical
    document compressions of arbitrary length.  The system outperforms
    both a baseline and a sentence-based compression system that
    operates by simplifying sequentially all sentences in a text.  Our
    results support the claim that discourse knowledge plays an
    important role in document summarization.
  },
  url = {http://pub.hal3.name/#daume02noisy}
}