Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment

Simple item page
dc.creatorBarzilay, Regina
dc.creatorLee, Lillian
dc.date2003-04-02
dc.date.accessioned2026-07-07T03:19:34Z
dc.date.available2026-07-07T03:19:34Z
dc.descriptionWe 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.
dc.descriptionProceedings of HLT-NAACL 2003 (Human Language Technology Conference)
dc.identifierhttps://arxiv.org/abs/cs/0304006
dc.identifierhttp://arxiv.org/abs/cs/0304006
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31514
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleLearning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment
dc.typetext

Files

Collections

arXiv