A statistical approach to machine translation
Computational Linguistics
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
A comparison of alignment models for statistical machine translation
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
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
Shallow parsing with conditional random fields
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Accurate unlexicalized parsing
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Improved statistical alignment models
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Hierarchical Phrase-Based Translation
Computational Linguistics
Decomposability of translation metrics for improved evaluation and efficient algorithms
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Syntactic models for structural word insertion and deletion
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
MT error detection for cross-lingual question answering
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
| Hi-index | 0.01 |
The treatment of 'spurious' words of source language is an important problem but often ignored in the discussion on phrase-based SMT. This paper explains why it is important and why it is not a trivial problem, and proposes three models to handle spurious source words. Experiments show that any source word deletion model can improve a phrase-based system by at least 1.6 BLEU points and the most sophisticated model improves by nearly 2 BLEU points. This paper also explores the impact of training data size and training data domain/genre on source word deletion.