We discuss here the need to define what we call an agent conversational language, a language for Embodied Conversational Agents (ECA) to have conversations with a human. We propose a set of Expressive Multimodal Conversation Acts (EMCA), which is based on the Expressive Speech Acts that we introduced in a previous work, enriched with the multimodal expression of the emotions linked to these act...

Visual data exploration poses challenges for ’InfoVis Novices’. A ’conversational interface’ which would enable users to generate and interact with visualizations through natural language and gestures, while maintaining a history of the data exploration, has the potential to ameliorate many of these challenges. We performed an exploratory, observational study designed to examine the role of suc...

Two tools for developing embodied conversational agents and deploying them over the world-wide web to standard web browsers are presented. DTask is a hierarchical task decomposition-based dialogue planner, based on the CEA-2018 task description language standard. LiteBody is an extensible, web-based BML renderer that runs in most contemporary web browsers with no additional software and provide...

Given the considerable importance of English language as a common method global communication, supporting and engaging learning environments for studying second are essential. In this study, we propose an interactive agent that considers differences in learners’ skill levels to help motivate learners support independent study. The proposed is AI chatbot can vary complexity its natural interacti...

INCORPORATING NON-VERBAL MODALITIES IN SPOKEN LANGUAGE UNDERSTANDING FOR MULTIMODAL CONVERSATIONAL SYSTEMS

’InfoVis novices’ have been found to struggle with visual data exploration. A ’conversational interface’ which would take natural language inputs to visualization generation and modification, while maintaining a history of the requests, visualizations and findings of the user, has the potential to ameliorate many of these challenges. We present Articulate2, initial work toward a conversational ...

Conversations are a new programming abstraction created for capturing knowledge about the interactions among agents. In this paper we review a conversational coordination language we have designed and used in the past few years, to characterize its main assumptions, strengths and limitations. Based on this analysis we discuss a number of major new features and extensions for our next generation...

Conversational partners can influence each other’s speaking patterns. In this paper, we aim to develop a computational model that infers influence levels directly from language samples. We propose a new approach to modeling linguistic influence in conversations based on a well-accepted model of social influence. Very generally, this approach assumes that an individual’s language model can be ex...