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

Marine Carpuat, Yuval Marton, Nizar HabashMach. Transl 2012 · DOI · OpenReview

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.
BibTeX
@article{carpuat2012improved,
  author = {Marine Carpuat and Yuval Marton and Nizar Habash},
  title = {{Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment}},
  journal = {Mach. Transl.},
  year = {2012},
  doi = {10.1007/s10590-011-9112-y},
}
Figure