The MIT-LL/AFRL IWSLT-2011 MT System

Abstract

This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2011 evaluation campaign. As part of these efforts, we experimented with a number of extensions to the standard phrase-based model that improve performance on the Arabic to English and English to French TED-talk translation tasks. We also applied our existing ASR system to the TED-talk lecture ASR task. We discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2010 system, and experiments we ran during the IWSLT-2011 evaluation. Specifically, we focus on 1) speech recognition for lecture-like data, 2) cross-domain translation using MAP adaptation, and 3) improved Arabic morphology for MT preprocessing.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 27, 2011
Accession Number
ADA576644

Entities

People

  • A. R. Aminzadeh
  • Brian Ore
  • Eric C Hansen
  • Jennifer Drexler
  • Ray Slyh
  • Terry Gleason
  • Tim Anderson
  • Wade Shen

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Automated Speech Recognition
  • Computational Linguistics
  • Computational Science
  • Cross Domain
  • Data Sets
  • Decoding
  • Department Of Defense
  • Language
  • Language Translation
  • Linguistics
  • Machine Translation
  • Natural Language Processing
  • Natural Languages
  • Standards

Fields of Study

  • Computer science

Readers

  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation