Prenominal modifier ordering via multiple sequence alignment

  • Authors:
  • Aaron Dunlop;Margaret Mitchell;Brian Roark

  • Affiliations:
  • Oregon Health & Science University, Portland, OR;University of Aberdeen, Aberdeen, Scotland, U.K.;Oregon Health & Science University, Portland, OR

  • Venue:
  • HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Producing a fluent ordering for a set of prenominal modifiers in a noun phrase (NP) is a problematic task for natural language generation and machine translation systems. We present a novel approach to this issue, adapting multiple sequence alignment techniques used in computational biology to the alignment of modifiers. We describe two training techniques to create such alignments based on raw text, and demonstrate ordering accuracies superior to earlier reported approaches.