Domain adaptation for translation models in statistical machine translation

Abstract

We investigate methods to adapt translation models in SMT to a specific target domain. We discuss two major problems, unknown words because of data sparseness in the (in-domain) training data, and ambiguities arising from out-of-domain parallel texts with different domain-specific translations. We propose novel solutions to both problems. The main contributions of this thesis are as follows:

We present a novel translation model architecture that supports domain adaptation at decoding time from a vector of component models. The combi

Show more