The true score of statistical paraphrase generation

Jonathan Chevelu, Ghislain Putois, Yves Lepage

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

This article delves into the scoring function of the statistical paraphrase generation model. It presents an algorithm for exact computation and two applicative experiments. The first experiment analyses the behaviour of a statistical paraphrase generation decoder, and raises some issues with the ordering of n-best outputs. The second experiment shows that a major boost of performance can be obtained by embedding a true score computation inside a Monte-Carlo sampling based paraphrase generator.

Original languageEnglish
Pages144-152
Number of pages9
Publication statusPublished - 2010 Dec 1
Event23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China
Duration: 2010 Aug 232010 Aug 27

Conference

Conference23rd International Conference on Computational Linguistics, Coling 2010
CountryChina
CityBeijing
Period10/8/2310/8/27

    Fingerprint

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Chevelu, J., Putois, G., & Lepage, Y. (2010). The true score of statistical paraphrase generation. 144-152. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.