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

Download
  1. Get@NRC: Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment (Opens in a new window)
DOIResolve DOI: http://doi.org/10.1007/s10590-011-9112-y
AuthorSearch for: ; Search for: ; Search for:
TypeArticle
Journal titleMachine Translation
ISSN0922-6567
1573-0573
Volume26
Issue1-2
Pages105120; # of pages: 16
SubjectStatistical machine translation; Reordering; VS; Post-verbal subjects; Matrix subject; Subject detection; Word alignment; Dependency parsing
AbstractWe 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.
Publication date
LanguageEnglish
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedYes
NPARC number21270133
Export citationExport as RIS
Report a correctionReport a correction
Record identifierb822c6ac-5874-4beb-bb1f-501d403bb714
Record created2014-01-03
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)