Construction of a Chinese–English Verb Lexicon for Machine Translation and Embedded Multilingual Applications

  • Authors:

  • Bonnie Jean Dorr;Gina-Anne Levow;Dekang Lin

  • Affiliations:

  • University of Maryland Institute for Advanced Computer Studies, College Park, MD 20742, U.S.A. E-mail: bonnie@umiacs.umd.edu;University of Maryland Institute for Advanced Computer Studies, College Park, MD 20742, U.S.A. E-mail: gina@umiacs.umd.edu;University of Alberta, Edmonton, Alberta, Canada, T6G 2E8 E-mail: lindek@cs.ualberta.edu

  • Venue:
  • Machine Translation
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper addresses the problem of automatic acquisition of lexicalknowledge for rapid construction of engines for machine translationand embedded multilingual applications. We describe new techniquesfor large-scale construction of a Chinese–English verb lexicon and we evaluate the coverage and effectiveness of the resulting lexicon.Leveraging off an existing Chinese conceptual database called HowNetand a large, semantically rich English verb database, we usethematic-role information to create links between Chinese concepts andEnglish classes. We apply the metrics of recall and precision to evaluate the coverage and effectiveness of thelinguistic resources. The results of this work indicate that: (a) weare able to obtain reliable Chinese–English entries both with andwithout pre-existing semantic links between the two languages; (b) ifwe have pre-existing semantic links, we are able to produce a morerobust lexical resource by merging these with our semantically richEnglish database; (c) in our comparisons with manual lexicon creation,our automatic techniques were shown to achieve 62% precision,compared to a much lower precision of 10% for arbitrary assignment of semantic links.