Semiring frameworks and algorithms for shortest-distance problems
Journal of Automata, Languages and Combinatorics
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
An end-to-end discriminative approach to machine translation
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
ORANGE: a method for evaluating automatic evaluation metrics for machine translation
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
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 Minimum Bayes-Risk decoding for statistical machine translation
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
Complexity of finding the BLEU-optimal hypothesis in a confusion network
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Efficient extraction of oracle-best translations from hypergraphs
NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
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
Learning performance of a machine translation system: a statistical and computational analysis
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
A systematic analysis of translation model search spaces
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Fluency, adequacy, or HTER?: exploring different human judgments with a tunable MT metric
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Statistical Machine Translation
Statistical Machine Translation
OpenFst: a general and efficient weighted finite-state transducer library
CIAA'07 Proceedings of the 12th international conference on Implementation and application of automata
Expected sequence similarity maximization
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
On dual decomposition and linear programming relaxations for natural language processing
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Assessing phrase-based translation models with oracle decoding
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Local lexical adaptation in machine translation through triangulation: SMT helping SMT
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Improving reordering with linguistically informed bilingual n-grams
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Findings of the 2011 Workshop on Statistical Machine Translation
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Meteor 1.3: automatic metric for reliable optimization and evaluation of machine translation systems
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Exact decoding of phrase-based translation models through Lagrangian relaxation
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Learning to translate: a statistical and computational analysis
Advances in Artificial Intelligence
Hope and fear for discriminative training of statistical translation models
The Journal of Machine Learning Research
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
Optimized online rank learning 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
Oracle decoding as a new way to analyze phrase-based machine translation
Machine Translation
Hi-index | 0.00 |
The search space of Phrase-Based Statistical Machine Translation (PBSMT) systems can be represented as a directed acyclic graph (lattice). By exploring this search space, it is possible to analyze and understand the failures of PBSMT systems. Indeed, useful diagnoses can be obtained by computing the so-called oracle hypotheses, which are hypotheses in the search space that have the highest quality score. For standard SMT metrics, this problem is, however, NP-hard and can only be solved approximately. In this work, we present two new methods for efficiently computing oracles on lattices: the first one is based on a linear approximation of the corpus bleu score and is solved using generic shortest distance algorithms; the second one relies on an Integer Linear Programming (ILP) formulation of the oracle decoding that incorporates count clipping constraints. It can either be solved directly using a standard ILP solver or using Lagrangian relaxation techniques. These new decoders are evaluated and compared with several alternatives from the literature for three language pairs, using lattices produced by two PBSMT systems.