A maximum entropy approach to natural language processing
Computational Linguistics
Grafting: fast, incremental feature selection by gradient descent in function space
The Journal of Machine Learning Research
Exploiting auxiliary distributions in stochastic unification-based grammars
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Estimation of stochastic attribute-value grammars using an informative sample
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Precision and recall of machine translation
NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
A fast algorithm for feature selection in conditional maximum entropy modeling
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Using self-trained bilexical preferences to improve disambiguation accuracy
IWPT '07 Proceedings of the 10th International Conference on Parsing Technologies
Correlating human and automatic evaluation of a German surface realiser
ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Grafting-light: fast, incremental feature selection and structure learning of Markov random fields
Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Feature selection for fluency ranking
INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Reversible stochastic attribute-value grammars
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Hi-index | 0.00 |
Reversible stochastic attribute-value grammars (de Kok et al., 2011) use one model for parse disambiguation and fluency ranking. Such a model encodes preferences with respect to syntax, fluency, and appropriateness of logical forms, as weighted features. Reversible models are built on the premise that syntactic preferences are shared between parse disambiguation and fluency ranking. Given that reversible models also use features that are specific to parsing or generation, there is the possibility that the model is trained to rely on these directional features. If this is true, the premise that preferences are shared between parse disambiguation and fluency ranking does not hold. In this work, we compare and apply feature selection techniques to extract the most discriminative features from directional and reversible models. We then analyse the contributions of different classes of features, and show that reversible models do rely on task-independent features.