Large-Scale Statistical Machine Translation with Weighted Finite State Transducers

  • Authors:

  • Graeme Blackwood;Adrià de Gispert;Jamie Brunning;William Byrne

  • Affiliations:

  • Machine Intelligence Laboratory, Department of Engineering, Cambridge University, Trumpington Street, Cambridge, CB2 1PZ, U.K., {gwb24,ad465,jjjb2,wjb31}@cam.ac.uk;Machine Intelligence Laboratory, Department of Engineering, Cambridge University, Trumpington Street, Cambridge, CB2 1PZ, U.K., {gwb24,ad465,jjjb2,wjb31}@cam.ac.uk;Machine Intelligence Laboratory, Department of Engineering, Cambridge University, Trumpington Street, Cambridge, CB2 1PZ, U.K., {gwb24,ad465,jjjb2,wjb31}@cam.ac.uk;Machine Intelligence Laboratory, Department of Engineering, Cambridge University, Trumpington Street, Cambridge, CB2 1PZ, U.K., {gwb24,ad465,jjjb2,wjb31}@cam.ac.uk

  • Venue:
  • Proceedings of the 2009 conference on Finite-State Methods and Natural Language Processing: Post-proceedings of the 7th International Workshop FSMNLP 2008
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Cambridge University Engineering Department phrase-based statistical machine translation system follows a generative model of translation and is implemented by the composition of component models of translation and movement realised as Weighted Finite State Transducers. Our flexible architecture requires no special purpose decoder and readily handles the large-scale natural language processing demands of state-of-the-art machine translation systems. In this paper we describe the CUED system's participation in the NIST 2008 Arabic-English machine translation evaluation task.