No description available.

Embodied Conversational Agents (ECA) form part of a range of virtual characters whose intended purpose include engaging in natural conversations with human users. While works in literature are ripe with descriptions of attempts at producing viable ECA architectures, few authors have addressed the role of episodic memory models in conversational agents. This form of memory, which provides a sense of autobiographic record-keeping in humans, has only recently been peripherally integrated into dialog management tools for ECAs. In our work, we propose to take a closer look at the shared characteristics of episodic memory models in recent examples from the field. Additionally, we propose several enhancements to these existing models through a unified episodic memory model for ECA's. As part of our research into episodic memory models, we present a process for determining the prevalent contexts in the conversations obtained from the aforementioned interactions. The process presented demonstrates the use of statistical and machine learning services, as well as Natural Language Processing techniques to extract relevant snippets from conversations. Finally, mechanisms to store, retrieve, and recall episodes from previous conversations are discussed. A primary contribution of this research is in the context of contemporary memory models for conversational agents and cognitive architectures. To the best of our knowledge, this is the first attempt at providing a comparative summary of existing works. As implementations of ECAs become more complex and encompass more realistic conversation engines, we expect that episodic memory models will continue to evolve and further enhance the naturalness of conversations.

Les systèmes de dialogues sont à même de révolutionner l'interaction entre l'homme et la machine. Pour autant, les efforts pour concevoir des agents conversationnels se sont souvent révélés infructueux, et ceux, malgré les dernières avancées en apprentissage profond et par renforcement. Les systèmes de dialogue palissent de devoir opérer sur de nombreux domaines d'application mais pour lesquels aucune mesure d'évaluation claire n'a été définie. Aussi, cette thèse s'attache à étudier les dialogues débouchant sur un objectif clair (goal-oriented dialogue) permettant de guider l'entrainement, et ceci, dans des environnements multimodaux. Plusieurs raisons expliquent ce choix : (i) cela contraint le périmètre de la conversation, (ii) cela introduit une méthode d'évaluation claire, (iii) enfin, l'aspect multimodal enrichie la représentation linguistique en reliant l'apprentissage du langage avec des expériences sensorielles. En particulier, nous avons développé GuessWhat?! (Qu-est-ce donc?!), un jeu imagé coopératif où deux joueurs tentent de retrouver un objet en posant une série de questions. Afin d’apprendre aux agents de répondre aux questions sur les images, nous avons développés une méthode dites de normalisation conditionnée des données (Conditional Batch Nornalization). Ainsi, cette méthode permet d'adapter simplement mais efficacement des noyaux de convolutions visuels en fonction de la question en cours. Enfin, nous avons étudié les tâches de navigation guidée par dialogue, et introduit la tâche Talk the Walk (Raconte-moi le Chemin) à cet effet. Dans ce jeu, deux agents, un touriste et un guide, s'accordent afin d'aider le touriste à traverser une reconstruction virtuelle des rues de New-York et atteindre une position prédéfinie. / While dialogue systems have the potential to fundamentally change human-machine interaction, developing general chatbots with deep learning and reinforce-ment learning techniques has proven difficult. One challenging aspect is that these systems are expected to operate in broad application domains for which there is not a clear measure of evaluation. This thesis investigates goal-oriented dialogue tasks in multi-modal environments because it (i) constrains the scope of the conversa-tion, (ii) comes with a better-defined objective, and (iii) enables enriching language representations by grounding them to perceptual experiences. More specifically, we develop GuessWhat, an image-based guessing game in which two agents cooper-ate to locate an unknown object through asking a sequence of questions. For the subtask of visual question answering, we propose Conditional Batch Normalization layers as a simple but effective conditioning method that adapts the convolutional activations to the specific question at hand. Finally, we investigate the difficulty of dialogue-based navigation by introducing Talk The Walk, a new task where two agents (a “tourist” and a “guide”) collaborate to have the tourist navigate to target locations in the virtual streets of New York City.