Word Reordering Approaches for Bangla-English Statistical Machine Translation

Entities Mentioned

• Bangla
• Bleu
• SMT
• Simon Fraser

1. We apply several word reordering techniques to a Bangla-English Statistical Machine Translation (SMT) system. We evaluate the approaches through their impact on the BLEU score for the phrase-based Bangla-English SMT system. According to the experimental results, automatic reordering rules have the most significant impact on the BLEU score. We also provide a new test set with multiple references between Bangla and English for SMT evaluation purposes and evaluate the reordering approaches on the extended test set. Content Type Book ChapterDOI 10.1007/978-3-642-13059-5_29Authors Maxim Roy, Simon Fraser University School of Computing Science Burnaby BC Canada V5A1S6Fred Popowich, ... (Read Full Article)

   Bookmark or Share this article

   
   

   Related Articles

   • Now, Indian translation a click away
   • also categorized in Machine Translation
   • Ectaco (usa) and C -Technologies (Sweden) Bring a New Generation ...
   • also categorized in Machine Translation
   • Machine translation system incorporating syntactic dependency treelets into a statistical framework
   • also mentions Bleu
   • Asia Online & Across Partner to Link Translation Services Into Business Processes
   • also categorized in Machine Translation
   • Gartner identifies seven grand challenges facing IT
   • also categorized in Machine Translation

   • Machine Translation system to be launched in September
   • also categorized in Machine Translation
   • Ectaco (usa) and C -Technologies (Sweden) Bring a New Generation ...
   • also categorized in Machine Translation
   • Updated Loqu8 Insight software integrates Microsoft Outlook support for ...
   • also categorized in Machine Translation
   • Translation and Localization Industry Pricing Survey Reveals While Demand is Up ...
   • also categorized in Machine Translation
   • Automatic Identification of Legal Terms in Czech Law Texts
   • also published in SpringerLink Home

Login to comment.