This page contains the paraphrases extracted by the process described in "Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment", Regina Barzilay and Lillian Lee, Proceedings of HLT-NAACL 2003, pp. 16--23 (ps, pdf, other formats)

As stated in the abstract of that paper, we address the text-to-text generation problem of sentence-level paraphrasing --- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered from unannotated comparable corpora: it learns a set of paraphrasing patterns represented by word lattice pairs and automatically determines how to apply these patterns to rewrite new sentences. The results of our evaluation experiments show that the system derives accurate paraphrases, outperforming baseline systems.

More info: Draft of an informal explanation of how the algorithm learns to generate sentence-level paraphrases

Press mentions:

BibTeX entry:

  author =       {Regina Barzilay and Lillian Lee},
  title =        {Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment},
  booktitle =    "HLT-NAACL 2003: Main Proceedings",
  year =         2003
The creation of this website is based upon work supported in part by the National Science Foundation under grant ITR/IM IIS-0081334 an Alfred P. Sloan Research Fellowship. Any opinions, findings, and conclusions or recommendations expressed above are those of the authors and do not necessarily reflect the views of the National Science Foundation or the Sloan Foundation.

Regina Barzilay
Lillian Lee
Cornell NLP homepage