Minimum error rate training in statistical machine translation
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Generation of word graphs in statistical machine translation
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
A hierarchical phrase-based model for statistical machine translation
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Discriminative training via linear programming
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Minimum risk annealing for training log-linear models
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Algorithms for Reporting and Counting Geometric Intersections
IEEE Transactions on Computers
Numerical Recipes 3rd Edition: The Art of Scientific Computing
Numerical Recipes 3rd Edition: The Art of Scientific Computing
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
Lattice Minimum Bayes-Risk decoding 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
Syntax augmented machine translation via chart parsing
StatMT '06 Proceedings of the Workshop on Statistical Machine Translation
Bilingually Motivated Word Segmentation for Statistical Machine Translation
ACM Transactions on Asian Language Information Processing (TALIP)
Lattice Minimum Bayes-Risk decoding for statistical machine translation
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
11,001 new features for statistical machine translation
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Using a dependency parser to improve SMT for subject-object-verb languages
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Using a maximum entropy model to build segmentation lattices for MT
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Domain adaptation for statistical machine translation with monolingual resources
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Stabilizing minimum error rate training
StatMT '09 Proceedings of the Fourth 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
Joint decoding with multiple translation models
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 2 - Volume 2
Consensus training for consensus decoding in machine translation
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
Metric and reference factors in minimum error rate training
Machine Translation
Fast consensus hypothesis regeneration for machine translation
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
Minimum error rate training by sampling the translation lattice
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Automatically learning source-side reordering rules for large scale machine translation
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Phrase clustering for smoothing TM probabilities: or, how to extract paraphrases from phrase tables
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Large scale parallel document mining for machine translation
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Machine translation with lattices and forests
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Finite-state models for speech-based search on mobile devices
Natural Language Engineering
Enriching document representation via translation for improved monolingual information retrieval
Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
The RWTH system combination system for WMT 2011
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Optimal search for minimum error rate training
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Inducing sentence structure from parallel corpora for reordering
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Quasi-synchronous phrase dependency grammars for machine translation
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Minimum imputed risk: unsupervised discriminative training for machine translation
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
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
Batch tuning strategies for statistical machine translation
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Learning to translate with multiple objectives
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
A class-based agreement model for generating accurately inflected translations
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Maximum expected BLEU training of phrase and lexicon translation models
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
A systematic comparison of phrase table pruning techniques
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Syntax-aware phrase-based statistical machine translation: system description
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Direct error rate minimization for statistical machine translation
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Lattice BLEU oracles in machine translation
ACM Transactions on Speech and Language Processing (TSLP)
Hi-index | 0.00 |
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring system performance can directly be optimized in training. To accomplish this, the training procedure determines for each feature function its exact error surface on a given set of candidate translations. The feature function weights are then adjusted by traversing the error surface combined over all sentences and picking those values for which the resulting error count reaches a minimum. Typically, candidates in MERT are represented as N-best lists which contain the N most probable translation hypotheses produced by a decoder. In this paper, we present a novel algorithm that allows for efficiently constructing and representing the exact error surface of all translations that are encoded in a phrase lattice. Compared to N-best MERT, the number of candidate translations thus taken into account increases by several orders of magnitudes. The proposed method is used to train the feature function weights of a phrase-based statistical machine translation system. Experiments conducted on the NIST 2008 translation tasks show significant runtime improvements and moderate BLEU score gains over N-best MERT.