Leveraging supplemental representations for sequential transduction

  • Authors:

  • Aditya Bhargava;Grzegorz Kondrak

  • Affiliations:

  • University of Toronto, Toronto, ON, Canada;University of Alberta, Edmonton, AB, Canada

  • Venue:
  • NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Sequential transduction tasks, such as grapheme-to-phoneme conversion and machine transliteration, are usually addressed by inducing models from sets of input-output pairs. Supplemental representations offer valuable additional information, but incorporating that information is not straightforward. We apply a unified reranking approach to both grapheme-to-phoneme conversion and machine transliteration demonstrating substantial accuracy improvements by utilizing heterogeneous transliterations and transcriptions of the input word. We describe several experiments that involve a variety of supplemental data and two state-of-the-art transduction systems, yielding error rate reductions ranging from 12% to 43%. We further apply our approach to system combination, with error rate reductions between 4% and 9%.