Theory of linear and integer programming
Theory of linear and integer programming
A systematic comparison of various statistical alignment models
Computational Linguistics
The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Fast and optimal decoding for machine translation
Artificial Intelligence
HMM-based word alignment in statistical translation
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2
Improved statistical alignment models
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
A phrase-based, joint probability model for statistical machine translation
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Symmetric word alignments for statistical machine translation
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
A discriminative matching approach to word alignment
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Word alignment via quadratic assignment
HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Hierarchical Phrase-Based Translation
Computational Linguistics
The complexity of phrase alignment problems
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
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
A new objective function for word alignment
ILP '09 Proceedings of the Workshop on Integer Linear Programming for Natural Langauge Processing
Theory of alignment generators and applications to statistical machine translation
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Why generative phrase models underperform surface heuristics
StatMT '06 Proceedings of the Workshop on Statistical Machine Translation
Probabilistic word alignment under the L0-norm
CoNLL '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning
| Hi-index | 0.00 |
Prior work on training the IBM-3 translation model is based on suboptimal methods for computing Viterbi alignments. In this paper, we present the first method guaranteed to produce globally optimal alignments. This not only results in improved alignments, it also gives us the opportunity to evaluate the quality of standard hillclimbing methods. Indeed, hill-climbing works reasonably well in practice but still fails to find the global optimum for between 2% and 12% of all sentence pairs and the probabilities can be several tens of orders of magnitude away from the Viterbi alignment. By reformulating the alignment problem as an Integer Linear Program, we can use standard machinery from global optimization theory to compute the solutions. We use the well-known branch-and-cut method, but also show how it can be customized to the specific problem discussed in this paper. In fact, a large number of alignments can be excluded from the start without losing global optimality.