The Rapidly Changing Landscape of Conversational Agents

TL;DR

This survey reviews the evolution of conversational agents, covering various approaches, challenges, and current state-of-the-art models, highlighting key developments and ongoing issues in the field.

Contribution

It provides a comprehensive overview of the history, methodologies, and challenges of conversational agents, integrating diverse approaches and identifying open problems.

Findings

Neural and generative models dominate current research

Major challenges include context understanding and trust issues

Lack of standardized metrics hampers comparison

Abstract

Conversational agents have become ubiquitous, ranging from goal-oriented systems for helping with reservations to chit-chat models found in modern virtual assistants. In this survey paper, we explore this fascinating field. We look at some of the pioneering work that defined the field and gradually move to the current state-of-the-art models. We look at statistical, neural, generative adversarial network based and reinforcement learning based approaches and how they evolved. Along the way we discuss various challenges that the field faces, lack of context in utterances, not having a good quantitative metric to compare models, lack of trust in agents because they do not have a consistent persona etc. We structure this paper in a way that answers these pertinent questions and discusses competing approaches to solve them.