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

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

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.
Proceedings of HLT-NAACL 2003 (Human Language Technology Conference)

Keywords

Computation and Language, I.2.7

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/31514

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cs/0304006
 http://arxiv.org/abs/cs/0304006

Collections

arXiv