Title: Pattern discovery in annotated dialogues using dynamic programming

Authors: Thierry Lecroq; Alexandre Pauchet; Émilie Chanoni; Gerardo Ayala Solano

Addresses: Université de Rouen, LITIS EA 4108, 76821 Mont-Saint-Aignan Cedex, France. ' INSA-Rouen, LITIS EA 4108, BP 08-76801 Saint-Étienne-du-Rouvray, France. ' Université de Rouen, Psy. NCA EA 4306, 76821 Mont-Saint-Aignan Cedex, France. ' INSA-Rouen, LITIS EA 4108, BP 08-76801 Saint-Étienne-du-Rouvray, France

Abstract: This study describes a new heuristic to discover behavioural patterns in annotated dialogues: firstly, dialogues are transcribed and annotated; then, two-dimensional patterns are extracted; finally, the semantic pertinence of the extracted patterns can be evaluated by an expert. The dialogues are annotated by using a grid designed by the expert. Recurrent patterns are extracted in the annotated dialogues using dynamic programming with the help of a substitution matrix specifically designed for the task. This article focuses on the method developed for extracting the patterns and presents as application some extracted patterns on annotations of dialogues between parents and children during the narration of child stories.

Keywords: pattern discovery; dynamic programming; semi-automatic dialogue analysis; annotated dialogues; behavioural patterns; semantics; parent narration; child stories; parent-children dialogues.

DOI: 10.1504/IJIIDS.2012.050097

International Journal of Intelligent Information and Database Systems, 2012 Vol.6 No.6, pp.603 - 618

Accepted: 29 Apr 2012
Published online: 23 Aug 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article