A study of tree adjoining grammars
A study of tree adjoining grammars
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Using lexicalized tags for machine translation
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Synchronous tree-adjoining grammars
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Minimum error rate training in statistical machine translation
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Head-Driven Statistical Models for Natural Language Parsing
Computational Linguistics
Scalable inference and training of context-rich syntactic translation models
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
N-gram-based Machine Translation
Computational Linguistics
SPMT: statistical machine translation with syntactified target language phrases
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
SSST '08 Proceedings of the Second Workshop on Syntax and Structure in Statistical Translation
SSST '07 Proceedings of the NAACL-HLT 2007/AMTA Workshop on Syntax and Structure in Statistical Translation
Simple, accurate parsing with an all-fragments grammar
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Corpus creation for new genres: A crowdsourced approach to PP attachment
CSLDAMT '10 Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk
A decoder for probabilistic synchronous tree insertion grammars
ATANLP '10 Proceedings of the 2010 Workshop on Applications of Tree Automata in Natural Language Processing
Non-isomorphic forest pair translation
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Statistical machine translation with a factorized grammar
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Generating referring expressions in context: the GREC task evaluation challenges
Empirical methods in natural language generation
String-to-dependency statistical machine translation
Computational Linguistics
Incremental syntactic language models for phrase-based translation
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Adjoining tree-to-string translation
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Semantic mapping using automatic word alignment and semantic role labeling
SSST-5 Proceedings of the Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation
Tree parsing with synchronous tree-adjoining grammars
IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies
Bayesian symbol-refined tree substitution grammars for syntactic parsing
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Hi-index | 0.00 |
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves translation quality without becoming computationally intractable. Using adjoining to model optionality allows general translation patterns to be learned without the clutter of endless variations of optional material. The appropriate modifiers can later be spliced in as needed. In this paper, we describe a novel method for learning a type of Synchronous Tree Adjoining Grammar and associated probabilities from aligned tree/string training data. We introduce a method of converting these grammars to a weakly equivalent tree transducer for decoding. Finally, we show that adjoining results in an end-to-end improvement of +0.8 Bleu over a baseline statistical syntax-based MT model on a large-scale Arabic/English MT task.