Domain Adaptation of Maximum Entropy Language Models

We investigate a recently proposed Bayesian adaptation method for building style-adapted maximum entropy language models for speech recognition, given a large corpus of written language data and a small corpus of speech transcripts. Experiments show that the method consistently outperforms linear interpolation which is typically used in such cases.

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Tanel Alumäe, Mikko Kurimo
• Keywords: ACL 2010, Bayesian Adaptation Method, Computational Linguistics, Entropy Language Models, Large Corpus