Language Model Adaptation for Statistical Machine Translation based on Information Retrieval


Matthias Eck, Stephan Vogel, Alex Waibel

Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA (matteck@cs.cmu.edu, vogel+@cs.cmu.edu, ahw@cs.cmu.edu)




Language modeling is an important part for both speech recognition and machine translation systems. Adaptation has been successfully applied to language models for speech recognition. In this paper we present experiments concerning language model adaptation for statistical machine translation. We develop a method to adapt language models using information retrieval methods. The adapted language models drastically reduce perplexity over a general language model and we can show that it is possible to improve the translation quality of a statistical machine translation using those adapted language models instead of a general language model.


Language Modeling, Statistical Machine Translation, Adaptation, Information Retrieval

Language(s) English, Chinese, Arabic
Full Paper