The MIT-LL/AFRL IWSLT-2010 MT System

Abstract

This paper describes the MIT-LL/AFRL Statistical Machine Translation (SMT) and the improvements that were developed during the IWSLT2010 evaluation campaign. As part of these efforts, we experimented with a number of extensions to the standard phrase-based model to improve performance on the Arabic and Turkish translations tasks. We also participated in the new French to English BTEC and English to French TALK tasks. We discuss the architecture of the MIT-LL/AFRL SMT systems, improvements over our 2009 system, and experiments we ran during the International Workshop on Spoken Language Translation 2010 evaluation. Specifically we focus on 1) cross-domain translation using MAP adaptation, 2) Turkish morphological processing and translation, 3) improved Arabic morphology for machine translation preprocessing, and 4) system combination methods for machine translation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 2011
Accession Number
ADA580388

Entities

People

  • A. R. Aminzadeh
  • Ray Slyh
  • Tim Anderson
  • Wade Shen

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Automated Speech Recognition
  • Computational Science
  • Cross Domain
  • Data Sets
  • Decoding
  • Department Of Defense
  • Government Procurement
  • Governments
  • Language
  • Language Translation
  • Military Research
  • Natural Language Processing
  • Preprocessing
  • Standards
  • Translations

Fields of Study

  • Computer science

Readers

  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation