Research Catalog

Title

Empirical methods for exploiting parallel texts / I. Dan Melamed.

Author

Melamed, I. Dan.

Publication

Cambridge, Mass. : MIT Press, [2001], ©2001.

Items in the Library & Off-site

Holdings

Details

Description

x, 195 pages : illustrations; 24 cm

Summary

• "Parallel texts (bitexts) are a goldmine of linguistic knowledge, because the translation of a text into another language can be viewed as a detailed annotation of what that text means. Knowledge about translational equivalence, which can be gleaned from bitexts, is of central importance for applications such as machine translation, cross-language information retrieval, and corpus linguistics.
• The availability of bitexts has increased dramatically since the advent of the Web, making their study an exciting new area of research in natural language processing. This book lays out the theory and the practical techniques for discovering and applying translational equivalence at the lexical level. It is a start-to-finish guide to designing and evaluating many translingual applications."--BOOK JACKET.

Subject

• Machine translating
• Linguistic models

Note

• Revision of the author's thesis.

Bibliography (note)

• Includes bibliographical references (p. [187]-192) and index.

Contents

1. Introduction -- I. Translational Equivalence Among Word Tokens. 2. A Geometric Approach to Mapping Bitext Correspondence. 3. Application: Alignment. 4. Application: Automatic Detection of Omissions in Translations -- II. The Type-Token Interface. 5. Models of Co-occurrence. 6. Manual Annotation of Translational Equivalence -- III. Translational Equivalence Among Word Types. 7. Word-to-Word Models of Translational Equivalence. 8. Automatic Discovery of Non-Compositional Compounds. 9. Sense-to-Sense Models of Translational Equivalence. 10. Summary and Outlook. A. Annotation Style Guide for the Blinker Project.

ISBN

0262133806 (hc. : alk. paper)

LCCN

00038028

OCLC

• ocm43859493
• SCSB-4094200

Owning Institutions

Columbia University Libraries