Distributional phrasal paraphrase generation for statistical machine translation

  • Authors:
  • Yuval Marton

  • Affiliations:
  • University of Maryland, Columbia University, and IBM T.J. Watson Research Center, Bellevue, WA

  • Venue:
  • ACM Transactions on Intelligent Systems and Technology (TIST) - Special Sections on Paraphrasing; Intelligent Systems for Socially Aware Computing; Social Computing, Behavioral-Cultural Modeling, and Prediction
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Paraphrase generation has been shown useful for various natural language processing tasks, including statistical machine translation. A commonly used method for paraphrase generation is pivoting [Callison-Burch et al. 2006], which benefits from linguistic knowledge implicit in the sentence alignment of parallel texts, but has limited applicability due to its reliance on parallel texts. Distributional paraphrasing [Marton et al. 2009a] has wider applicability, is more language-independent, but doesn't benefit from any linguistic knowledge. Nevertheless, we show that using distributional paraphrasing can yield greater gains in translation tasks. We report method improvements leading to higher gains than previously published, of almost 2 Bleu points, and provide implementation details, complexity analysis, and further insight into this method.