Evaluating Translational Correspondence Using Annotation Projection

Abstract

Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependence. Underlying these models is an assumption about the directness of translational correspondence between sentences in the two languages; however, the extent to which this assumption is valid and useful is not well understood. In this paper, we present an empirical study that quantifies the degree to which syntactic dependencies are preserved when parses are projected directly from English to Chinese. Our results show that although the direct correspondence assumption is often too restrictive, a small set of principled, elementary linguistic transformations can boost the quality of the projected Chinese parses by 76% relative to the unimproved baseline.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2003
Accession Number
ADA455137

Entities

People

  • Amy Weinberg
  • Okan Kolak
  • Philip Resnik
  • Rebecca Hwa

Organizations

  • University of Maryland

Tags

Communities of Interest

  • C4I
  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computational Linguistics
  • Computational Science
  • Construction
  • Error Analysis
  • Grammars
  • Language
  • Linguistics
  • Machine Translation
  • Markov Models
  • Models
  • Natural Language Processing
  • Spanish Language
  • Standards
  • Universities

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Economics
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation