Ultraconservative online algorithms for multiclass problems
The Journal of Machine Learning Research
Decoding complexity in word-replacement translation models
Computational Linguistics
BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Minimum error rate training in statistical machine translation
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Online Passive-Aggressive Algorithms
The Journal of Machine Learning Research
Hierarchical Phrase-Based Translation
Computational Linguistics
Minimum risk annealing for training log-linear models
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Moses: open source toolkit for statistical machine translation
ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
Online large-margin training of syntactic and structural translation features
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Lattice-based minimum error rate training for statistical machine translation
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Regularization and search for minimum error rate training
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
Further meta-evaluation of machine translation
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Optimal search for minimum error rate training
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
| Hi-index | 0.00 |
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formulation, the algorithm uses N-best lists output by the decoder to grow the Translation Pool that shapes the surface on which the actual optimization is performed. Recent work has been done to extend the algorithm to use the entire translation lattice built by the decoder, instead of N-best lists. We propose here a third, intermediate way, consisting in growing the translation pool using samples randomly drawn from the translation lattice. We empirically measure a systematic improvement in the BLEU scores compared to training using N-best lists, without suffering the increase in computational complexity associated with operating with the whole lattice.