Detection of Translational Equivalence

Abstract

I propose a general algorithm for detecting translational equivalence between text samples in different languages. This algorithm is based on current approaches to duplicate detection, and it relies on information which can be automatically learned from parallel text. I also show experimental results which support the hypothesis that translational equivalence is empirically observable. In addition, these results suggest profitable directions for improving performance on this recognition task.1.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2001
Accession Number
ADA458755

Entities

People

  • Noah A. Smith

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Detection
  • Dictionaries
  • Information Operations
  • Iterations
  • Language
  • Machine Learning
  • Translations
  • Universities
  • Words (Language)

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Computer Vision.
  • Theoretical Analysis.