Paper: Phrase Table Training for Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?

ACL ID P08-1010
Title Phrase Table Training for Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

In this work, the problem of extracting phrase translation is formulated as an information re- trieval process implemented with a log-linear model aiming for a balanced precision and re- call. We present a generic phrase training al- gorithm which is parameterized with feature functions and can be optimized jointly with the translation engine to directly maximize the end-to-end system performance. Multiple data-driven feature functions are proposed to capture the quality and confidence of phrases andphrasepairs. Experimentalresultsdemon- strate consistent and significant improvement over the widely used method that is based on word alignment matrix only.