Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue

We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the goal is to establish universe details, and to collaborate on an interesting story in that universe, through a series of natural dialogue exchanges. Our model can augment any probabilistic conversational agent by allowing it to reason about universe information established and what potential next utterances might reveal. Ideally, with each utterance, agents would reveal just enough information to add specificity and reduce ambiguity without limiting the conversation. We empirically show that our model allows control over the rate at which the agent reveals information and that doing so significantly improves accuracy in predicting the next line of dialogues from movies. We close with a case-study with four professional theatre performers, who preferred interactions with our model-augmented agent over an unaugmented agent.

[1]  Claude E. Shannon,et al.  Prediction and Entropy of Printed English , 1951 .

[2]  Saul A. Kripke,et al.  Semantical Analysis of Modal Logic I Normal Modal Propositional Calculi , 1963 .

[3]  Joseph Weizenbaum,et al.  ELIZA—a computer program for the study of natural language communication between man and machine , 1966, CACM.

[4]  K. Johnstone IMPRO: Improvisation and Theatre , 1979 .

[5]  T. Trabasso,et al.  Causal relatedness and importance of story events , 1985 .

[6]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

[7]  Thorsten Joachims,et al.  A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization , 1997, ICML.

[8]  C. McLeod The use of Keith Johnstone's concepts of 'Circles of Expectation' and Vogler's generic story structure as directorial aids in comedy theatre , 2000 .

[9]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[10]  Robert Michael Young,et al.  From linear story generation to branching story graphs , 2005, IEEE Computer Graphics and Applications.

[11]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[12]  John D. Lafferty,et al.  Dynamic topic models , 2006, ICML.

[13]  Timothy Bickmore,et al.  Health dialog systems for patients and consumers , 2006, J. Biomed. Informatics.

[14]  Jim Bizzocchi Games and Narrative: An Analytical Framework , 2007 .

[15]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[16]  Jim Bizzochi Games and Narrative: An Analytical Framework , 2007 .

[17]  Kevin K. Brown The Auslander Test: or, ‘Of Bots and Humans’ , 2008 .

[18]  Gyllian Raby Improvisation and Devising: The Circle of Expectation, the Invisible Hand, and RSVP , 2010 .

[19]  Dirk Geeraerts,et al.  Theories of Lexical Semantics , 2010 .

[20]  Saif Mohammad,et al.  From Once Upon a Time to Happily Ever After: Tracking Emotions in Novels and Fairy Tales , 2011, LaTeCH@ACL.

[21]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[22]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[23]  A Savvy Robot Standup Comic: Online Learning through Audience Tracking , 2015 .

[24]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

[25]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[26]  R. Michael Young,et al.  Plotter: Operationalizing the Master Book of All Plots , 2015, INT/SBG@AIIDE.

[27]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[28]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[29]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[30]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[31]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[32]  Mark O. Riedl,et al.  Improvisational Computational Storytelling in Open Worlds , 2016, ICIDS.

[33]  Christopher M. Danforth,et al.  The emotional arcs of stories are dominated by six basic shapes , 2016, EPJ Data Science.

[34]  Adam S. Miner,et al.  Talking to Machines About Personal Mental Health Problems. , 2017, JAMA.

[35]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[36]  Eric P. Xing,et al.  Toward Controlled Generation of Text , 2017, ICML.

[37]  Iyad Rahwan,et al.  Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm , 2017, EMNLP.

[38]  Chuang Gan,et al.  Recurrent Topic-Transition GAN for Visual Paragraph Generation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[39]  Piotr W. Mirowski,et al.  Improvised Theatre Alongside Artificial Intelligences , 2021, AIIDE.

[40]  K. Fitzpatrick,et al.  Delivering Cognitive Behavior Therapy to Young Adults With Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial , 2017, JMIR mental health.

[41]  Mark O. Riedl,et al.  Improvisational Storytelling Agents , 2017 .

[42]  Jason Weston,et al.  Learning End-to-End Goal-Oriented Dialog , 2016, ICLR.

[43]  Piotr W. Mirowski,et al.  Improvised Comedy as a Turing Test , 2017, ArXiv.

[44]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[45]  Rahul Goel,et al.  On Evaluating and Comparing Open Domain Dialog Systems , 2018 .

[46]  Quan Hoang,et al.  Predicting Movie Genres Based on Plot Summaries , 2018, ArXiv.

[47]  Jörg Tiedemann,et al.  OpenSubtitles2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora , 2018, LREC.

[48]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[49]  Lukasz Kaiser,et al.  Generating Wikipedia by Summarizing Long Sequences , 2018, ICLR.

[50]  Nan Hua,et al.  Universal Sentence Encoder , 2018, ArXiv.

[51]  Marcos Báez,et al.  Smart Conversational Agents for Reminiscence , 2018, 2018 IEEE/ACM 1st International Workshop on Software Engineering for Cognitive Services (SE4COG).

[52]  Jesse Hoey,et al.  Affective Neural Response Generation , 2017, ECIR.

[53]  Rahul Goel,et al.  On Evaluating and Comparing Conversational Agents , 2018, ArXiv.

[54]  Jason Weston,et al.  Retrieve and Refine: Improved Sequence Generation Models For Dialogue , 2018, SCAI@EMNLP.

[55]  Percy Liang,et al.  Generating Sentences by Editing Prototypes , 2017, TACL.