View in EDS

Self-Organizing Example-Based Machine Translation, A Prototype.

Saved in:

Bibliographic Details
Title:	Self-Organizing Example-Based Machine Translation, A Prototype.
Language:	English
Authors:	Juola, Patrick
Peer Reviewed:	N
Page Count:	8
Publication Date:	1995
Document Type:	Reports - Descriptive
Descriptors:	Algorithms, Computational Linguistics, English, Evaluation Methods, French, Grammar, Machine Translation, Uncommonly Taught Languages, Urdu
Geographic Terms:	U.S.; Colorado
Abstract:	This paper describes an attempt to combine the advantages of both example-based translation and stochastic translation methods in an attempt to develop a method for inferring symbolic transfer functions from a bilingual corpus. By formalizing the translation process and applying standard optimization techniques, a system can be developed that will identify grammatical categories and produce coherent transfer functions between languages. The validity of this approach is demonstrated in a prototype system that can learn transfer functions between English, French, and Urdu. Contains 13 references. (Author)
Journal Code:	RIEAUG1995
Entry Date:	1995
Accession Number:	ED380987
Database:	ERIC

Description
Abstract:	This paper describes an attempt to combine the advantages of both example-based translation and stochastic translation methods in an attempt to develop a method for inferring symbolic transfer functions from a bilingual corpus. By formalizing the translation process and applying standard optimization techniques, a system can be developed that will identify grammatical categories and produce coherent transfer functions between languages. The validity of this approach is demonstrated in a prototype system that can learn transfer functions between English, French, and Urdu. Contains 13 references. (Author)