An efficient A* search algorithm for statistical machine translation

  • Authors:
  • Franz Josef Och;Nicola Ueffing;Hermann Ney

  • Affiliations:
  • University of Technology, Aachen, Germany;University of Technology, Aachen, Germany;University of Technology, Aachen, Germany

  • Venue:
  • DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we describe an efficient A* search algorithm for statistical machine translation. In contrary to beam-search or greedy approaches it is possible to guarantee the avoidance of search errors with A*. We develop various so-phisticated admissible and almost admissible heuristic functions. Especially our newly developped method to perform a multi-pass A* search with an iteratively improved heuristic function allows us to translate even long sentences. We compare the A* search algorithm with a beam-search approach on the Hansards task.