Combining Evidence from Homologous Datasets

Abstract

With Machine Translation and/or Automatic Speech Recognition, there can be different versions of the same data with distinct expressions. We argue that combining evidence from these "homologous" datasets can give us better representation of the original data, and our experiments show that a model combining all sources outperforms each individual dataset in retrieval.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2006
Accession Number
ADA454795

Entities

People

  • Ao Feng
  • James Allan

Organizations

  • University of Massachusetts Amherst

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Applied Computer Science
  • Artificial Intelligence
  • Automated Speech Recognition
  • Computer Languages
  • Computer Science
  • Hard Copy
  • Information Operations
  • Information Retrieval
  • Language
  • Law
  • Linguistics
  • Machine Translation
  • Translations
  • Urban Areas

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Geospatial Intelligence and Artificial Intelligence Analytics
  • Materials Science and Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks