Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
The Journal of Machine Learning Research
Modelling and detecting decisions in multi-party dialogue
SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue
Policy recognition in the abstract hidden Markov model
Journal of Artificial Intelligence Research
The infinite HMM for unsupervised PoS tagging
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Unsupervised classification of dialogue acts using a dirichlet process mixture model
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Automatic decision detection in meeting speech
MLMI'07 Proceedings of the 4th international conference on Machine learning for multimodal interaction
Analysing meeting records: an ethnographic study and technological implications
MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
INTERACT'05 Proceedings of the 2005 IFIP TC13 international conference on Human-Computer Interaction
Hi-index | 0.00 |
We investigate hierarchical graphical models (HGMs) for automatically detecting decisions in multi-party discussions. Several types of dialogue act (DA) are distinguished on the basis of their roles in formulating decisions. HGMs enable us to model dependencies between observed features of discussions, decision DAs, and subdialogues that result in a decision. For the task of detecting decision regions, an HGM classifier was found to outperform non-hierarchical graphical models and support vector machines, raising the F1-score to 0.80 from 0.55.