Generalizing Word Lattice Translation

Abstract

Word lattice decoding has proven useful in spoken language translation; we argue that it provides a compelling model for translation of text genres, as well. We extend lattice decoding to hierarchical phrase-based models, providing a unified treatment with phrase-based decoding by treating lattices as a case of weighted finite-state automata. In the process, we resolve a significant complication that lattice representations introduce in reordering models. Our experiments evaluating the approach demonstrate substantial gains for Chinese-English and Arabic-English translation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2008
Accession Number
ADA481994

Entities

People

  • Christopher Dyer
  • Philip Resnik
  • Smaranda Muresan

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Coding
  • Computational Linguistics
  • Computers
  • Context Free Grammars
  • Decoding
  • Formal Languages
  • Grammars
  • Language
  • Language Translation
  • Linguistics
  • Machine Translation
  • Machines
  • Natural Language Processing
  • Recognition
  • Translations

Readers

  • Computational Fluid Dynamics (CFD)
  • Computational Linguistics