Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Discriminative Reranking for Natural Language Parsing
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
PCFG models of linguistic tree representations
Computational Linguistics
The TREC question answering track
Natural Language Engineering
Kernel Methods for Pattern Analysis
Kernel Methods for Pattern Analysis
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
An SVM based voting algorithm with application to parse reranking
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Introduction to the CoNLL-2003 shared task: language-independent named entity recognition
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Using LTAG based features in parse reranking
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Discriminative Reranking for Natural Language Parsing
Computational Linguistics
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Boosting-based parse reranking with subtree features
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Tree kernels for semantic role labeling
Computational Linguistics
Re-ranking models based-on small training data for spoken language understanding
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
Practical very large scale CRFs
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
On dual decomposition and linear programming relaxations for natural language processing
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Efficient convolution kernels for dependency and constituent syntactic trees
ECML'06 Proceedings of the 17th European conference on Machine Learning
Efficiently inducing features of conditional random fields
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Comparing Stochastic Approaches to Spoken Language Understanding in Multiple Languages
IEEE Transactions on Audio, Speech, and Language Processing
| Hi-index | 0.01 |
Reranking models have been successfully applied to many tasks of Natural Language Processing. However, there are two aspects of this approach that need a deeper investigation: (i) Assessment of hypotheses generated for reranking at classification phase: baseline models generate a list of hypotheses and these are used for reranking without any assessment; (ii) Detection of cases where reranking models provide a worst result: the best hypothesis provided by the reranking model is assumed to be always the best result. In some cases the reranking model provides an incorrect hypothesis while the baseline best hypothesis is correct, especially when baseline models are accurate. In this paper we propose solutions for these two aspects: (i) a semantic inconsistency metric to select possibly more correct n-best hypotheses, from a large set generated by an SLU basiline model. The selected hypotheses are reranked applying a state-of-the-art model based on Partial Tree Kernels, which encode SLU hypotheses in Support Vector Machines with complex structured features; (ii) finally, we apply a decision strategy, based on confidence values, to select the final hypothesis between the first ranked hypothesis provided by the baseline SLU model and the first ranked hypothesis provided by the re-ranker. We show the effectiveness of these solutions presenting comparative results obtained reranking hypotheses generated by a very accurate Conditional Random Field model. We evaluate our approach on the French MEDIA corpus. The results show significant improvements with respect to current state-of-the-art and previous re-ranking models.