The syntactic process
BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Coupling CCG and hybrid logic dependency semantics
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank
Computational Linguistics
Wide-coverage efficient statistical parsing with ccg and log-linear models
Computational Linguistics
Dependency-based n-gram models for general purpose sentence realisation
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Exploiting named entity classes in CCG surface realization
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
Tree linearization in English: improving language model based approaches
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
Probabilistic models for disambiguation of an HPSG-based chart generator
Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology
Incorporating information status into generation ranking
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Perceptron reranking for CCG realization
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Designing agreement features for realization ranking
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
The first surface realisation shared task: overview and evaluation results
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
: from deep representation to surface
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
| Hi-index | 0.00 |
Comprehension and corpus studies have found that the tendency to minimize dependency length has a strong influence on constituent ordering choices. In this paper, we investigate dependency length minimization in the context of discriminative realization ranking, focusing on its potential to eliminate egregious ordering errors as well as better match the distributional characteristics of sentence orderings in news text. We find that with a state-of-the-art, comprehensive realization ranking model, dependency length minimization yields statistically significant improvements in BLEU scores and significantly reduces the number of heavy/light ordering errors. Through distributional analyses, we also show that with simpler ranking models, dependency length minimization can go overboard, too often sacrificing canonical word order to shorten dependencies, while richer models manage to better counterbalance the dependency length minimization preference against (sometimes) competing canonical word order preferences.