Hierarchical phrase-based translation with weighted finite state transducers

  • Authors:

  • Gonzalo Iglesias;Adrià de Gispert;Eduardo R. Banga;William Byrne

  • Affiliations:

  • University of Vigo, Vigo, Spain;University of Cambridge, Cambridge, U.K.;University of Vigo, Vigo, Spain;University of Cambridge, Cambridge, U.K.

  • Venue:
  • NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes a lattice-based decoder for hierarchical phrase-based translation. The decoder is implemented with standard WFST operations as an alternative to the well-known cube pruning procedure. We find that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search errors, direct generation of translation lattices in the target language, better parameter optimization, and improved translation performance when rescoring with long-span language models and MBR decoding. We report translation experiments for the Arabic-to-English and Chinese-to-English NIST translation tasks and contrast the WFST-based hierarchical decoder with hierarchical translation under cube pruning.