Shallow Dialogue Processing Using Machine Learning Algorithms (or not)

Zufferey, Sandrine; Popescu-Belis, Andrei; Clark, Alex; Georgescul, Maria; Lalanne, Denis (2005). Shallow Dialogue Processing Using Machine Learning Algorithms (or not). In: Bengio, Samy; Bourlard, Hervé (eds.) Machine Learning for Multimodal Interaction. Lecture Notes in Computer Science: Vol. 3361 (pp. 277-290). Berlin: Springer 10.1007/978-3-540-30568-2_24

[img] Text
chp%3A10.1007%2F978-3-540-30568-2_24.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (148kB)

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.

Item Type:

Book Section (Book Chapter)

Division/Institute:

06 Faculty of Humanities > Department of Linguistics and Literary Studies > Institute of French Language and Literature

UniBE Contributor:

Zufferey, Sandrine

Subjects:

800 Literature, rhetoric & criticism > 840 French & related literatures
400 Language > 440 French & related languages

ISSN:

0302-9743

ISBN:

978-3-540-24509-4

Series:

Lecture Notes in Computer Science

Publisher:

Springer

Language:

English

Submitter:

Sandrine Zufferey

Date Deposited:

25 Apr 2016 11:53

Last Modified:

05 Dec 2022 14:53

Publisher DOI:

10.1007/978-3-540-30568-2_24

BORIS DOI:

10.7892/boris.78684

URI:

https://boris.unibe.ch/id/eprint/78684

Actions (login required)

Edit item Edit item
Provide Feedback