Statistical phrase-based translation
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
A hierarchical phrase-based model for statistical machine translation
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Beyond log-linear models: boosted minimum error rate training for N-best Re-ranking
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Random restarts in minimum error rate training for statistical machine translation
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
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
An empirical study on development set selection strategy for machine translation learning
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Lessons from NRC's Portage system at WMT 2010
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Discriminative instance weighting for domain adaptation in statistical machine translation
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Better hypothesis testing for statistical machine translation: controlling for optimizer instability
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
SampleRank training for phrase-based machine translation
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
The CMU-ARK German-English translation system
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Structured ramp loss minimization for machine translation
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Prediction of learning curves in machine translation
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Optimization strategies for online large-margin learning in machine translation
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Hi-index | 0.00 |
The most commonly used method for training feature weights in statistical machine translation (SMT) systems is Och's minimum error rate training (MERT) procedure. A well-known problem with Och's procedure is that it tends to be sensitive to small changes in the system, particularly when the number of features is large. In this paper, we quantify the stability of Och's procedure by supplying different random seeds to a core component of the procedure (Powell's algorithm). We show that for systems with many features, there is extensive variation in outcomes, both on the development data and on the test data. We analyze the causes of this variation and propose modifications to the MERT procedure that improve stability while helping performance on test data.