Lilia, A Showcase for Fast Bootstrap of Conversation-Like Dialogues Based on a Goal-Oriented System - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Lilia, A Showcase for Fast Bootstrap of Conversation-Like Dialogues Based on a Goal-Oriented System

Bassam Jabaian
Stéphane Huet
Fabrice Lefèvre

Résumé

Recently many works have proposed to cast human-machine interaction in a sentence generation scheme. Neural networks models can learn how to generate a probable sentence based on the user's statement along with a partial view of the dialogue history. While appealing to some extent, these approaches require huge training sets of general-purpose data and lack a principled way to intertwine language generation with information retrieval from back-end resources to fuel the dialogue with actualised and precise knowledge. As a practical alternative, in this paper, we present Lilia, a showcase for fast bootstrap of conversation-like dialogues based on a goal-oriented system. First, a comparison of goal-oriented and conversational system features is led, then a conversion process is described for the fast bootstrap of a new system, finalised with an on-line training of the system's main components. Lilia is dedicated to a chitchat task, where speakers exchange viewpoints on a displayed image while trying collaboratively to derive its author's intention. Evaluations with user trials showed its efficiency in a realistic setup.
Fichier principal
Vignette du fichier
SLSP19.pdf (264.53 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02333916 , version 1 (25-10-2019)

Identifiants

Citer

Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre. Lilia, A Showcase for Fast Bootstrap of Conversation-Like Dialogues Based on a Goal-Oriented System. 7th International Conference on Statistical Language and Speech Processing (SLSP), 2019, Ljublljana, Slovenia. pp.31-43, ⟨10.1007/978-3-030-31372-2_3⟩. ⟨hal-02333916⟩
91 Consultations
130 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More