Development of Chinese-English Machine Translation System.

Abstract

The report documents progress and results of a 2-1/3 year effort to further develop the prototype Chinese-English Machine Translation System. Additional rules were incorporated into the existing grammer for Chinese analysis and interlingual transfer, with emphasis on the latter. CHIDIC was updated and revised. Approximately 16,000 new entries were added to CHIDIC, bringing the total available entries to over 73,000. Linguistic work on a random access dictionary incorporating feature notation was carried out. A new design for the translation system was initiated and partially programmed for conversion of the current system from a CDC 6400 version into an IBM version. Better control of the parsing process was achieved by improving the segmentation procedures during input, and by addition of more revealing diagnostic printouts as steps toward reduction of spurious ambiguities. The Model 600D Chinese Teleprinter System was used for the first time to prepare large batches of texts for input. A total of 307 pages of machine readable texts, comprising 300,000 characters were prepared during this report. (Author)

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1974
Accession Number
AD0776813

Entities

People

  • Stephen W. Chan
  • William S-y. Wang

Organizations

  • University of California, Berkeley

Tags

DTIC Thesaurus Topics

  • Ambiguity
  • Applied Computer Science
  • Computational Science
  • Computer Vision
  • Conversion
  • Dictionaries
  • Machine Translation
  • Models
  • Notation
  • Personality
  • Prototypes
  • Teleprinters
  • Translations

Readers

  • Computational Linguistics
  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Software Engineering

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation