Development of Domain-Specific Scenarios for Training and Evaluation of Two-Way, Free Form, Spoken Language Translation Devices

Abstract

To create effective and accurate two-way, free form, spoken language translation devices, the technologies must have appropriate training data. The goal of the Defense Advanced Research Projects Agency Spoken Language Communication and Translation System for Tactical Use (TRANSTAC) program is to demonstrate capabilities to rapidly develop and field this technology, so speakers of different languages can communicate in real-world tactical situations. A critical component is to generate data sets to train and evaluate the technologies. A novel approach was developed to collect these data, employing innovative data-collection and evaluation scenarios. This article describes the scenario methodology used for the TRANSTAC data collections and evaluations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2010
Accession Number
ADA522914

Entities

People

  • Brian A. Weiss
  • Marnie Menzel

Organizations

  • National Institute of Standards and Technology

Tags

Communities of Interest

  • Biomedical
  • Human Systems
  • Weapons Technologies

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Civic Action
  • Civil Affairs
  • Data Sets
  • Electronic Mail
  • Engineering
  • Improvised Explosive Devices
  • Language
  • Language Translation
  • Machine Translation
  • Mechanical Engineering
  • Military Personnel
  • Natural Language Processing
  • Standards
  • Test And Evaluation
  • Training
  • Translations

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Instructional Design and Training Evaluation.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.