Intention and Face in Dialog

TL;DR

This paper explores how intentions influence politeness and face acts in dialogue, using computational models to classify face acts and analyze their relation to intentions, advancing understanding of social dynamics in conversation.

Contribution

It introduces a new state-of-the-art model for classifying face acts and demonstrates how integrating dialog act annotations reveals the close link between intentions and face acts.

Findings

Face act classification achieved new state-of-the-art performance.

Dialog acts improve detection of minority face act classes.

Intentions are closely related to face acts, influencing politeness strategies.

Abstract

The notion of face described by Brown and Levinson (1987) has been studied in great detail, but a critical aspect of the framework, that which focuses on how intentions mediate the planning of turns which impose upon face, has received far less attention. We present an analysis of three computational systems trained for classifying both intention and politeness, focusing on how the former influences the latter. In politeness theory, agents attend to the desire to have their wants appreciated (positive face), and a complementary desire to act unimpeded and maintain freedom (negative face). Similar to speech acts, utterances can perform so-called face acts which can either raise or threaten the positive or negative face of the speaker or hearer. We begin by using an existing corpus to train a model which classifies face acts, achieving a new SoTA in the process. We then observe that every face act has an underlying intention that motivates it and perform additional experiments integrating dialog act annotations to provide these intentions by proxy. Our analysis finds that dialog acts improve performance on face act detection for minority classes and points to a close relationship between aspects of face and intent.