Shallow Dialogue Processing Using Machine Learning Algorithms (or Not)

16 years 10 days ago

Download andreipb.free.fr

This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staﬀ or business meetings. Four components of the model are deﬁned, and several machine learning techniques are used to extract features from dialogue transcripts: maximum entropy classiﬁers for dialogue acts, latent semantic analysis for topic segmentation, or decision tree classiﬁers for discourse markers. A rule-based approach is proposed for solving cross-modal references to meeting documents. The methods are trained and evaluated thanks to a common data set and annotation format. The integration of the components into an automated shallow dialogue parser opens the way to multimodal meeting processing and retrieval applications.

Andrei Popescu-Belis, Alexander Clark, Maria Georg

Real-time Traffic

Dialogue | MLMI 2004 | Shallow Dialogue | Shallow Dialogue Analysis |

claim paper

» A Hybrid Ontology Directed Feedback Selection Algorithm for Supporting Creative Problem So...

» Antelogue Pronoun Resolution for Text and Dialogue

» Experimental Evaluation of TreeBased Algorithms for Intonational Breaks Representation

» A Multimodal Discourse Ontology for Meeting Understanding

» Guided Conversations about Leadership Mentoring with Movies and Interactive Characters

Post Info
More Details (n/a)

Added	02 Jul 2010
Updated	02 Jul 2010
Type	Conference
Year	2004
Where	MLMI
Authors	Andrei Popescu-Belis, Alexander Clark, Maria Georgescul, Denis Lalanne, Sandrine Zufferey

Comments (0)

Sciweavers

Shallow Dialogue Processing Using Machine Learning Algorithms (or Not)

Dialogue | MLMI 2004 | Shallow Dialogue | Shallow Dialogue Analysis |

Explore & Download

Productivity Tools

Sciweavers