A Generative Model of Group Conversation Hannah Morrison Chris - - PowerPoint PPT Presentation

A Generative Model of Group Conversation

Hannah Morrison Chris Martens

About Me

• Junior at North Carolina State University
• Favorite games: Transistor, Hellblade: Senua’s

Sacrifice, Life is Strange, Overwatch

https://lh3.googleusercontent.com/bv677TeGn5sOGjMud3zSqJBNPec1Ip_ 2w5Y1oN6J9q0pAdLDWAn_F-WezvE0SykrWHiP1v5rYmhhzODwobJUvelL 4V-q=s300 http://www.hellblade.com/new-hellblade-title-poster/

Introduction

• Why is character believability important?
• Character personality is built through conversation

Introduction

Example: Overwatch

Overwatch Uprising 000. Digital Image. Blizzard Press Center. Blizzard Entertainment. Web. Reference Kit: Symmetra. Digital image. Play Overwatch. Blizzard Entertainment. Web. "Symmetra/Quotes." Overwatch Wiki. Gamepedia, 21 Apr. 2017. Web. 17 July 2017. "Uprising/Quotes." Overwatch Wiki. Gamepedia, 30 May 2017. Web. 17 July 2017.

Introduction

Example: Dragon Age: Inquisition

http://dragonage.wikia.com/wiki/Cassandra_Pentaghast/Dialogue http://gamingtrend.com/wp-content/uploads/2014/11/Dragon-Age-Inquisition-Preview-01.jpg

Introduction

Problem: hand-authoring conversations

https://www.polygon.com/e3/2017/6/14/15803834/detroit-become-humans-e3-2017-script-david-cage https://www.vg247.com/2015/09/23/until-dawns-script-was-10000-pages-long/ https://gamerant.com/witcher-3-script-length/

Solution: generative conversation models

The Model

Outline:

• Approach

– Related Work – Overview – Conversation – Agent Personality – Emotion – Belief Change

• Example Conversation
• Results/Analysis
• Future Work

The Model: Related Work

• Inspired by Ryan et al., Short and Evans
• Based rules on work by Stodgill, Johnson and Johnson,

Gibson

• Written in Ceptre

– Linear-logic based modeling language

Richard Evans and Emily Short. 2014. Versu—a simulationist storytelling system. IEEE Transactions on Computational Intelligence and AI in Games 6, 2 (2014), 113–130 James Ryan, Michael Mateas, and Noah Wardrip-Fruin. 2016. A lightweight videogame dialogue manager. Proc. DiGRA–FDG (2016). David R Gibson. 2003. Participation shifts: Order and differentiation in group conversation. Social forces 81, 4 (2003), 1335–1380 David W Johnson and Frank P Johnson. 1991. Joining together: Group theory and group skills. Prentice-Hall, Inc. Ralph M Stogdill. 1959. Individual behavior and group achievement: A theory; the experimental evidence. (1959). Chris Martens. 2015. Ceptre: A language for modeling generative interactive systems. In Eleventh Artificial Intelligence and Interactive Digital Entertainment Conference.

The Model: Overview

• “The Model” = Ceptre Program
• Conversation topics and characters are hard-coded

– may be changed by the author

• Characters can have changing opinions and emotions,

have personalities

• Output: conversational skeletons
• No goal-oriented behavior (yet)

The Model: Overview

This is Alice. This is Bob. This is Carol.

The Model: Overview

Let’s talk about the weather. Current State:

• Alice, Bob, and Carol like each other.
• Alice, Bob, and Carol feel content.
• Alice has the Participant personality.
• Bob has the People Pleaser

Personality.

• Carol has the Contrarian Personality.
• Alice and Carol have a positive opinion
• f the weather.
• Bob has a negative opinion of the

weather.

• Current Topic: Weather

Initial State:

• Alice, Bob, and Carol like

each other.

• Alice, Bob, and Carol feel

content.

• Alice has the Participant

personality.

• Bob has the People

Pleaser Personality.

• Carol has the Contrarian

Personality.

• Alice and Bob have a

positive opinion of the weather.

• Carol has a negative
• pinion of the weather.
• Current Topic: None

Rule: Initiate Conversation Shorthand: State Change:

• Current Topic: Weather

(Rule: Initiate Conversation)

The Model: Conversation

• Rules (mostly) enforce conversational norms and flow

– e.g. only one person may speak at a time Example interrupt: if C is the type of person to interrupt someone and C’ is currently speaking then C interrupts C’ and C is currently speaking and C’ feels miffed

The Model: Conversation

I think-- I think the weather is horrible! State Change:

• Alice is speaking.

(Rule: Begin Speaking) State Change:

• Carol is speaking.

(Rule: Interrupt)

• Alice feels miffed.

(Rule: Interrupt)

The Model: Personality

• Personality Archetypes: Participant, People-Pleaser,

Contrarian, Reticent

• Rules only accessible to certain personality archetypes

Example: agree to please: if C hears C’ say their opinion on a topic and C is a People-Pleaser then C vocalizes agreement with C’

The Model: Personality

I agree, Carol. The weather is too hot. State Change:

• Bob is speaking.

(Rule: Agree to Please)

The Model: Emotion

• Rules describe emotional state transitions
• Characters can feel encouraged, dejected, miffed,

angry, content Example: upset from interruption: if C feels miffed twice then C feels angry

The Model: Emotion

I think-- I think the weather is awful! State Change:

• Alice is speaking.

(Rule: Begin Speaking) State Change:

• Carol is speaking.

(Rule: Interrupt)

• Alice is angry.

(Rule: Upset From Interruption)

The Model: Belief Change

• Rules depict changing sentiments of the characters
• Characters can have a positive, negative, or neutral

sentiment regarding a topic Example: negative to neutral opinion: if C has a negative opinion about the current topic and C hears C’ voice a positive

• pinion about the current topic then C has a neutral opinion

about the current topic

The Model: Belief Change

I like the

• weather. I think

the weather is perfect for swimming. State Change:

• Alice is speaking.

(Rule: Begin Speaking/Finish Speaking) Maybe the weather isn’t as bad as I thought. State Change:

• Carol has a neutral opinion
• f the weather.

(Rule: Negative to Neutral Opinion)

The Model

Outline:

• Approach

– Related Work – Overview – Conversation – Agent Personality – Emotion – Belief Change

• Example Conversation
• Results/Analysis
• Future Work

The Model: Example Conversation

The Model

Outline:

• Approach

– Related Work – Overview – Conversation – Agent Personality – Emotion – Belief Change

• Example Conversation
• Results/Analysis
• Future Work

The Model: Analysis

• Expressive range: range of outcomes the model is

capable of generating – Goal: produce a variety of meaningful outcomes

• To test: run the program with different combinations of

inputs – A few outcomes: not good – Many outcomes: good

The Model: Analysis

Future Work

• Add natural-language generation
• Add depth to belief change
• Add wider range of social interactions

Future Work

• Games

– Automate non-story-essential conversations

• Social Skills Training

– Help practice interacting in groups

• Combine these areas

Conclusion

• Conversations are a fundamental part of narrative and

character development, but authoring them is time consuming

• We created a generative model of conversation
• Our model generates dynamic, diverse representations
• f conversations between groups of characters
• E-mail: hmorris3@ncsu.edu