A polynomial-time algorithm for statistical machine translation

  • Authors:
  • Dekai Wu

  • Affiliations:
  • University of Science and Technology, Clear Water Bay, Hong Kong

  • Venue:
  • ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

We introduce a polynomial-time algorithm for statistical machine translation. This algorithm can be used in place of the expensive, slow best-first search strategies in current statistical translation architectures. The approach employs the stochastic bracketing transduction grammar (SBTG) model we recently introduced to replace earlier word alignment channel models, while retaining a bigram language model. The new algorithm in our experience yields major speed improvement with no significant loss of accuracy.