BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
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
Hierarchical Phrase-Based Translation
Computational Linguistics
SSST '08 Proceedings of the Second Workshop on Syntax and Structure in Statistical Translation
Comparing reordering constraints for SMT using efficient Bleu oracle computation
SSST '07 Proceedings of the NAACL-HLT 2007/AMTA Workshop on Syntax and Structure in Statistical Translation
Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology
Demonstration of Joshua: an open source toolkit for parsing-based machine translation
ACLDemos '09 Proceedings of the ACL-IJCNLP 2009 Software Demonstrations
Context-free reordering, finite-state translation
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Assessing phrase-based translation models with oracle decoding
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Machine translation system combination by confusion forest
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Computing lattice BLEU oracle scores for machine translation
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Oracle decoding as a new way to analyze phrase-based machine translation
Machine Translation
Lattice BLEU oracles in machine translation
ACM Transactions on Speech and Language Processing (TSLP)
Hi-index | 0.00 |
Hypergraphs are used in several syntax-inspired methods of machine translation to compactly encode exponentially many translation hypotheses. The hypotheses closest to given reference translations therefore cannot be found via brute force, particularly for popular measures of closeness such as BLEU. We develop a dynamic program for extracting the so called oracle-best hypothesis from a hypergraph by viewing it as the problem of finding the most likely hypothesis under an n-gram language model trained from only the reference translations. We further identify and remove massive redundancies in the dynamic program state due to the sparsity of n-grams present in the reference translations, resulting in a very efficient program. We present runtime statistics for this program, and demonstrate successful application of the hypotheses thus found as the targets for discriminative training of translation system components.