Evaluation of Machine Translation Errors in English and Iraqi Arabic

Abstract

Errors in machine translations of English-Iraqi Arabic dialogues were analyzed at two different points in the systems' development using Human Translation Error Rate (HTER) methods to identify errors and human annotations to refine Translation Error Rate (TER) annotations. Although the frequencies of errors in the more mature systems were lower, the proportions of error types exhibited little change. Results include high frequencies of pronoun errors in translations to English, high frequencies of subject person inflection in translations to Iraqi Arabic, similar frequencies of word order errors in both translation directions, and very low frequencies of polarity errors. The problems with many errors can be generalized as the need to insert lexemes not present in the source or vice versa, which includes errors in multi-word expressions. Discourse context will be required to resolve some problems with deictic elements like pronouns.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2010
Accession Number
ADA576234

Entities

People

  • Andrew Freeman
  • Christy Doran
  • Dan Parvaz
  • John Aberdeen
  • Marwan Awad
  • Sherri Condon

Organizations

  • MITRE Corporation

Tags

DTIC Thesaurus Topics

  • Ambiguity
  • Applied Computer Science
  • Automated Speech Recognition
  • Computational Linguistics
  • Computational Science
  • Contrast
  • Corporations
  • Department Of Defense
  • Error Analysis
  • Errors
  • Frequency
  • Language
  • Machine Translation
  • Materials
  • Polarity
  • Test And Evaluation
  • Translations

Readers

  • Approximation Theory.
  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Translation