The AFRL-MITLL WMT15 System: There's More than One Way to Decode It!

Abstract

This paper describes the AFRL-MITLL statistical MT system and the improvements that were developed during the WMT15 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 Russian to English translation task creating three submission systems with different decoding strategies. Out of vocabulary words were addressed with named entity postprocessing.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 25, 2015
Accession Number
AD1034899

Entities

People

  • Brian J. Thompson
  • Christina May
  • Elizabeth E. Salesky
  • Grant Erdmann
  • Jeremy Gwinnup
  • Katherine Young
  • Michaeel M. Kazi
  • Timothy Anderson

Organizations

  • MIT Lincoln Laboratory

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Computational Linguistics
  • Decoding
  • English Language
  • Language
  • Language Translation
  • Linguistics
  • Machine Translation
  • Military Research
  • Natural Language Processing
  • Natural Languages
  • Neural Networks
  • Software Development
  • Standards
  • Test Sets
  • United States

Readers

  • Computational Fluid Dynamics (CFD)
  • Computational Linguistics