A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciences

TL;DR

This survey reviews recent neural models for conversation analysis, highlighting their strengths and limitations, and discusses integrating social science insights to improve understanding and generation of conversational behavior.

Contribution

It provides a comprehensive overview of neural architectures for conversation analysis and proposes integrating social science perspectives for more fundamental understanding.

Findings

Neural models effectively detect emotion, dialogue acts, sentiment.

Current models focus on limited conversational phenomena.

Integrating social science can enhance conversation analysis and generation.

Abstract

Some exciting new approaches to neural architectures for the analysis of conversation have been introduced over the past couple of years. These include neural architectures for detecting emotion, dialogue acts, and sentiment polarity. They take advantage of some of the key attributes of contemporary machine learning, such as recurrent neural networks with attention mechanisms and transformer-based approaches. However, while the architectures themselves are extremely promising, the phenomena they have been applied to to date are but a small part of what makes conversation engaging. In this paper we survey these neural architectures and what they have been applied to. On the basis of the social science literature, we then describe what we believe to be the most fundamental and definitional feature of conversation, which is its co-construction over time by two or more interlocutors. We discuss how neural architectures of the sort surveyed could profitably be applied to these more fundamental aspects of conversation, and what this buys us in terms of a better analysis of conversation and even, in the longer term, a better way of generating conversation for a conversational system.