Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment

  • Authors:

  • Marine Carpuat;Yuval Marton;Nizar Habash

  • Affiliations:

  • National Research Council, Gatineau, Canada J8X 3X7;IBM T. J. Watson Research Center, Yorktown Heights, USA 10598;Columbia University Center for Computational Learning Systems, New York, USA 10115

  • Venue:
  • Machine Translation
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

We study challenges raised by the order of Arabic verbs and their subjects in statistical machine translation (SMT). We show that the boundaries of post-verbal subjects (VS) are hard to detect accurately, even with a state-of-the-art Arabic dependency parser. In addition, VS constructions have highly ambiguous reordering patterns when translated to English, and these patterns are very different for matrix (main clause) VS and non-matrix (subordinate clause) VS. Based on this analysis, we propose a novel method for leveraging VS information in SMT: we reorder VS constructions into pre-verbal (SV) order for word alignment. Unlike previous approaches to source-side reordering, phrase extraction and decoding are performed using the original Arabic word order. This strategy significantly improves BLEU and TER scores, even on a strong large-scale baseline. Limiting reordering to matrix VS yields further improvements.