A maximum entropy approach to natural language processing
Computational Linguistics
A neural probabilistic language model
The Journal of Machine Learning Research
The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Discriminative training and maximum entropy models for statistical machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Journal of Computational and Applied Mathematics
Training neural network language models on very large corpora
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Improved language modeling for statistical machine translation
ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts
Continuous space language models
Computer Speech and Language
Joint morphological-lexical language modeling for machine translation
NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers
UCH-UPV English: Spanish system for WMT10
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Training continuous space language models: some practical issues
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
CEU-UPV English-Spanish system for WMT11
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Large, pruned or continuous space language models on a GPU for statistical machine translation
WLM '12 Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT
Neural network language models for off-line handwriting recognition
Pattern Recognition
Hi-index | 0.00 |
Statistical machine translation systems are based on one or more translation models and a language model of the target language. While many different translation models and phrase extraction algorithms 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 statistical 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 probability estimation. We consider the translation of European Parliament Speeches. This task is part of an international evaluation organized by the TC-STAR project in 2006. The proposed method achieves consistent improvements in the BLEU score on the development and test data. We also present algorithms to improve the estimation of the language model probabilities when splitting long sentences into shorter chunks.