Paper: Continuous Space Language Models For Statistical Machine Translation

ACL ID P06-2093
Title Continuous Space Language Models For Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

Statistical machine translation systems are based on one or more translation mod- els and a language model of the target language. While many different trans- lation models and phrase extraction al- gorithms have been proposed, a standard word n-gram back-off language model is used in most systems. In this work, we propose to use a new sta- tistical language model that is based on a continuous representation of the words in the vocabulary. A neural network is used to perform the projection and the proba- bility estimation. We consider the trans- lation of European Parliament Speeches. This task is part of an international evalua- tion organized by the TC-STAR project in 2006. The proposed method achieves con- sistent improvements in the BLEU score on the development and test data. We also ...