A Generic Machine Learning based Approach for Addressee Detection in Multiparty Interaction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

A Generic Machine Learning based Approach for Addressee Detection in Multiparty Interaction

Résumé

Addressee detection is one of the most fundamental tasks for seamless dialogue management and turn taking in human-agent interaction. Whereas addressee detection is implicit in dyadic interaction, it becomes a challenging task in multiparty interactions when more than two participants are involved. Existing research works employ either rule-based or statistical approaches for addressee detection. However, most of these works either have been tested on a single data set or only support a fixed number of participants. In this article, we propose a model based on generic features to predict the addressee in data sets with varying number of participants. The results tested on two different corpora show that the proposed model outperforms existing baselines.

Dates et versions

hal-02283234 , version 1 (10-09-2019)

Identifiants

Citer

Usman Malik, Mukesh Barange, Naser Ghannad, Julien Saunier, Alexandre Pauchet. A Generic Machine Learning based Approach for Addressee Detection in Multiparty Interaction. Intelligent Virtual Agents (IVA), Jul 2019, Paris, France. pp.119-126, ⟨10.1145/1122445.1122456⟩. ⟨hal-02283234⟩
101 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More