about
Conversational Agents: Theory and Applications (arxiv.org)
2 points by sebg on Mar 3, 2022 | hide | past | pdf | discuss on HN

In plain words: A survey of conversational agents, covering casual chatbots, goal-driven assistants, and animated characters, plus how they represent dialogue and how they are judged, with focus on accountability and interpretability. It maps uses in health and education and weighs the technology's benefits and societal risks.

Abstract

In this chapter, we provide a review of conversational agents (CAs), discussing chatbots, intended for casual conversation with a user, as well as task-oriented agents that generally engage in discussions intended to reach one or several specific goals, often (but not always) within a specific domain. We also consider the concept of embodied conversational agents, briefly reviewing aspects such as character animation and speech processing. The many different approaches for representing dialogue in CAs are discussed in some detail, along with methods for evaluating such agents, emphasizing the important topics of accountability and interpretability. A brief historical overview is given, followed by an extensive overview of various applications, especially in the fields of health and education. We end the chapter by discussing benefits and potential risks regarding the societal impact of current and future CA technology.

Mattias Wahde, Marco Virgolin
arXiv:2202.03164 · cs.CL, cs.AI · submitted Feb 7, 2022
abstract · pdf · html · preprint of a chapter to appear in Handbook of Computer Learning and Intelligence - Volume 1

add comment on HN