Convergence of the Nelder--Mead Simplex Method to a Nonstationary Point
SIAM Journal on Optimization
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
Generalizing local and non-local word-reordering patterns for syntax-based machine translation
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Accuracy-based scoring for DOT: towards direct error minimization for data-oriented translation
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Pattern Recognition Letters
Learning to transform and select elementary trees for improved syntax-based machine translations
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Discriminative feature-tied mixture modeling for statistical machine translation
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Optimal search for minimum error rate training
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Locally training the log-linear model for SMT
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Direct error rate minimization for statistical machine translation
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
| Hi-index | 0.00 |
We propose a variation of simplex-downhill algorithm specifically customized for optimizing parameters in statistical machine translation (SMT) decoder for better end-user automatic evaluation metric scores for translations, such as versions of BLEU, TER and mixtures of them. Traditional simplex-downhill has the advantage of derivative-free computations of objective functions, yet still gives satisfactory searching directions in most scenarios. This is suitable for optimizing translation metrics as they are not differentiable in nature. On the other hand, Armijo algorithm usually performs line search efficiently given a searching direction. It is a deep hidden fact that an efficient line search method will change the iterations of simplex, and hence the searching trajectories. We propose to embed the Armijo inexact line search within the simplex-downhill algorithm. We show, in our experiments, the proposed algorithm improves over the widely-applied Minimum Error Rate training algorithm for optimizing machine translation parameters.