The MIT-LL/AFRL MT System

Abstract

The MIT-LL/AFRL MT system is a statistical phrase-based translation system that implements many modern SMT training and decoding techniques. Our system was designed with the long term goal of dealing with corrupted ASR input for Speech-to-Speech MT applications. This paper will discuss the architecture of the MIT-LL/AFRL MT system, and experiments with manual and ASR transcription data that were run as part of the IWSLT-2005 Chinese-to-English evaluation campaign.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2005
Accession Number
ADA515050

Entities

People

  • Brian Delaney
  • Tim Anderson
  • Wade Shen

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Algorithms
  • Cost Estimates
  • Decoding
  • Distortion
  • English Language
  • Foreign Languages
  • Information Operations
  • Language
  • Machine Translation
  • Optimization
  • Test And Evaluation
  • Test Sets
  • Training
  • Translations

Readers

  • Computational Linguistics