Improvising Linguistic Style: Social and Affective Bases for Agent Personality

TL;DR

This paper presents a novel theory and algorithms for improvising linguistic style in artificial agents, enhancing their social and emotional expressiveness for more believable interactive characters.

Contribution

It introduces Linguistic Style Improvisation, combining speech act representations with improvisation algorithms to create socially oriented, believable AI characters.

Findings

Enables agents to improvise speech styles dynamically.

Supports socially oriented and believable character interactions.

Aligns with established improvisation criteria.

Abstract

This paper introduces Linguistic Style Improvisation, a theory and set of algorithms for improvisation of spoken utterances by artificial agents, with applications to interactive story and dialogue systems. We argue that linguistic style is a key aspect of character, and show how speech act representations common in AI can provide abstract representations from which computer characters can improvise. We show that the mechanisms proposed introduce the possibility of socially oriented agents, meet the requirements that lifelike characters be believable, and satisfy particular criteria for improvisation proposed by Hayes-Roth.