Challenges in Building Intelligent Open-domain Dialog Systems

TL;DR

This paper reviews recent neural approaches to open-domain dialog systems, focusing on overcoming challenges related to semantics, consistency, and interactiveness to improve long-term user engagement.

Contribution

It highlights key challenges and discusses recent neural methods addressing semantics, consistency, and interactiveness in open-domain dialog systems.

Findings

Neural methods improve understanding of social needs.

Ensuring system consistency builds user trust.

Enhancing interactiveness achieves social goals.

Abstract

There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI. Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging. This paper reviews the recent works on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness. Semantics requires a dialog system to not only understand the content of the dialog but also identify user's social needs during the conversation. Consistency requires the system to demonstrate a consistent personality to win users trust and gain their long-term confidence. Interactiveness refers to the system's ability to generate interpersonal responses to achieve particular social goals such as entertainment, conforming, and task completion. The works we select to present here is based on our unique views and are by no means complete. Nevertheless, we hope that the discussion will inspire new research in developing more intelligent dialog systems.