Date of Original Version

6-2002

Type

Conference Proceeding

Abstract or Description

Machine Translation of minority languages presents unique challenges, including the paucity of bilingual training data and the unavailability of linguistically-trained speakers. This paper focuses on a machine learning approach to transfer-based MT, where data in the form of translations and lexical alignments are elicited from bilingual speakers, and a seeded version-space learning algorithm formulates and refines transfer rules. A rule-generalization lattice is defined based on LFG-style f-structures, permitting generalization operators in the search for the most general rules consistent with the elicited data. The paper presents these methods and illustrates examples.

DOI

10.1007/3-540-45820-4_1

Share

COinS
 

Published In

S.D. Richardson (Ed.): AMTA 2002, LNAI 2499, 1-10.