EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
An empirical study on language model adaptation
ACM Transactions on Asian Language Information Processing (TALIP)
Approximation lasso methods for language modeling
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
A comparative study on language model adaptation techniques using new evaluation metrics
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Discriminative n-gram language modeling
Computer Speech and Language
Extending boosting for large scale spoken language understanding
Machine Learning
Extending boosting for large scale spoken language understanding
Machine Learning
Cascaded model adaptation for dialog act segmentation and tagging
Computer Speech and Language
Porting a lexicalized-grammar parser to the biomedical domain
Journal of Biomedical Informatics
Model adaptation via model interpolation and boosting for web search ranking
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Adapting boosting for information retrieval measures
Information Retrieval
Discriminative instance weighting for domain adaptation in statistical machine translation
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
ACM Transactions on Asian Language Information Processing (TALIP)
An empirical study on language model adaptation using a metric of domain similarity
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
| Hi-index | 0.00 |
In this paper, we contrast two language model adaptation approaches: MAP estimation and the perceptron algorithm. Used in isolation, we show that MAP estimation outperforms the latter approach, for reasons which argue for combining the two approaches. When combined, the resulting system provides a 0.7 percent absolute reduction in word error rate over MAP estimation alone. In addition, we demonstrate that, in a multi-pass recognition scenario, it is better to use the perceptron algorithm on early pass word lattices, since the improved error rate improves acoustic model adaptation.