PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Log-linear weight optimisation via Bayesian Adaptation in Statistical Machine Translation
Germán Sanchis-Trilles and Francisco Casacuberta
In: 23rd International Conference on Computational Linguistics (COLING2010), August 23-27, Beijing, China.

Abstract

In this paper, we present an adaptation technique for statistical machine translation, in which we apply the well-known Bayesian adaptation paradigm with the purpose of adapting the model parameters. Since state-of-the-art statistical machine translation systems model the translation process as a log-linear combination of simpler models, we present the formal derivation of how to apply such paradigm to the weights of the log-linear combination. We show empirical results in which a small amount of adaptation data is able to improve both the non-adapted system and a system which optimises the above-mentioned weights on the adaptation set only, while gaining both in reliability and speed.

EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:7431
Deposited By:Alfons Juan
Deposited On:17 March 2011