@Article{daume05alignments,
  author =       {Hal {Daum\'e III} and Daniel Marcu},
  title =        {Induction of Word and Phrase Alignments for Automatic Document Summarization}
  journal =      {Computational Linguistics},
  year =         {2005},
  month =        {December},
  volume =       {31},
  number =       {4},
  pages =        {505--530},
  abstract =     {
    Current research in automatic single document summarization is
    dominated by two effective, yet na\"ive approaches: summarization by
    sentence extraction, and headline generation via bag-of-words models.
    While successful in some tasks, neither of these models is able to
    adequately capture the large set of linguistic devices utilized by
    humans when they produce summaries.  One possible explanation for the
    widespread use of these models is that good techniques have been
    developed to extract appropriate training data for them from existing
    document/abstract and document/headline corpora.  We believe that
    future progress in automatic summarization will be driven both by the
    development of more sophisticated, linguistically informed models, as
    well as a more effective leveraging of document/abstract corpora.  In
    order to open the doors to simultaneously achieving both of these
    goals, we have developed techniques for automatically producing
    word-to-word and phrase-to-phrase \emph{alignments} between documents
    and their human-written abstracts.  These alignments make explicit the
    correspondences that exist in such document/abstract pairs, and create
    a potentially rich data source from which complex summarization
    algorithms may learn.  This paper describes experiments we have
    carried out to analyze the ability of \emph{humans} to perform such
    alignments, and based on these analyses, we describe experiments for
    creating them automatically.  Our model for the alignment task is
    based on an extension of the standard hidden Markov model, and learns
    to create alignments in a completely unsupervised fashion.  We
    describe our model in detail and present experimental results that
    show that our model is able to learn to reliably identify word- and
    phrase-level alignments in a corpus of \docabs\ pairs.
  },
  url = {http://pub.hal3.name/#daume05alignments}
}