ISSD-93 Selected papers presented at the international symposium on Spoken dialogue
A maximum entropy approach to natural language processing
Computational Linguistics
BoosTexter: A Boosting-based Systemfor Text Categorization
Machine Learning - Special issue on information retrieval
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Text classification using string kernels
The Journal of Machine Learning Research
Dialogue act modeling for automatic tagging and recognition of conversational speech
Computational Linguistics
Dialogue act tagging with Transformation-Based Learning
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
HMM and neural network based speech act detection
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Further progress in meeting recognition: the ICSI-SRI spring 2005 speech-to-text evaluation system
MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
Cascaded model adaptation for dialog act segmentation and tagging
Computer Speech and Language
Hi-index | 0.00 |
This paper evaluates the performance of various machine learning approaches and their combination for text based dialog act (DA) classification of meetings data. For this task, boosting and three other text based approaches previously described in the literature are used. To further improve the classification performance, three different combination schemes take into account the results of the individual classifiers. All classification methods are evaluated on the ICSI Meeting Corpus based on both reference transcripts and the output of a speech-to-text (STT) system. The results indicate that both the proposed boosting based approach and a method relying on maximum entropy substantially outperform the use of mini language models and a simple scheme relying on cue phrases. The best performance was achieved by combining individual methods with a multilayer perceptron.