Chart-Based Transfer Rule Application in Machine Translation

35"ansfer-based Machine Translation systems require a procedure for choosing the set; of transfer rules for generating a target language translation from a given source language sentence. In an MT system with many comI)eting transfer rules, choosing t;he best, set of transfer rules for translation may involve the evaluation of an explosive number of competing wets. We propose a sohltion t;o this problem l)ased on current bestfirst chart parsing algorithms.

• Type: Conference
• Year: 2000
• Where: COLING
• Authors: Adam Meyers, Michiko Kosaka, Ralph Grishman
• Keywords: 35"ansfer-based Machine Translation, COLING 2000, COLING 2008, Target Language Translation, Transfer Rules