Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs

Abstract

Conversational participants tend to immediately and unconsciously adapt to each other's language styles: a speaker will even adjust the number of articles and other function words in their next utterance in response to the number in their partner's immediately preceding utterance. This striking level of coordination is thought to have arisen as a way to achieve social goals, such as gaining approval or emphasizing difference in status. But has the adaptation mechanism become so deeply embedded in the language-generation process as to become a reflex? We argue that fictional dialogs offer a way to study this question, since authors create the conversations but don't receive the social benefits (rather, the imagined characters do). Indeed, we find significant coordination across many families of function words in our large movie-script corpus. We also report suggestive preliminary findings on the effects of gender and other features; e.g., surprisingly, for articles, on average, characters adapt more to females than to males.

data available at http://www.cs.cornell.edu/~cristian/movies

Cited by in corpus (78)

• A Literature Survey of Recent Advances in Chatbots
• Agnostic Federated Learning
• Conversational AI: The Science Behind the Alexa Prize
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
• Personalizing ASR for Dysarthric and Accented Speech with Limited Data
• You had me at hello: How phrasing affects memorability
• Echoes of power: Language effects and power differences in social interaction
• Personalized Dialogue Generation with Diversified Traits
• Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
• Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
• The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service
• Deep Learning Based Chatbot Models
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
• Gunrock 2.0: A User Adaptive Social Conversational System
• Variational Attention for Sequence-to-Sequence Models
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Progressive Memory Banks for Incremental Domain Adaptation
• A Hierarchical Latent Structure for Variational Conversation Modeling
• PONE: A Novel Automatic Evaluation Metric for Open-Domain Generative Dialogue Systems
• Auditing Data Provenance in Text-Generation Models
• Automatic Evaluation and Moderation of Open-domain Dialogue Systems
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
• Steering Output Style and Topic in Neural Response Generation
• TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
• Beam Search with Bidirectional Strategies for Neural Response Generation
• Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
• Gender Asymmetries in Reality and Fiction: The Bechdel Test of Social Media
• A Dataset for Document Grounded Conversations
• Deep Active Learning for Dialogue Generation
• Natural Language Generation with Neural Variational Models
• Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
• ALOHA: Artificial Learning of Human Attributes for Dialogue Agents
• A Tailored Pre-Training Model for Task-Oriented Dialog Generation
• Enterprise to Computer: Star Trek chatbot
• CraftAssist Instruction Parsing: Semantic Parsing for a Minecraft Assistant
• Affect-Driven Dialog Generation
• An Ensemble Model with Ranking for Social Dialogue
• Conditional Text Generation for Harmonious Human-Machine Interaction
• Audrey: A Personalized Open-Domain Conversational Bot
• Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
• Collaborative Storytelling with Human Actors and AI Narrators
• Affective Neural Response Generation
• An Evaluation Protocol for Generative Conversational Systems
• Designing dialogue systems: A mean, grumpy, sarcastic chatbot in the browser
• Find the Conversation Killers: a Predictive Study of Thread-ending Posts
• Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner
• Federated Natural Language Generation for Personalized Dialogue System
• Discovering Useful Sentence Representations from Large Pretrained Language Models
• Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model
• Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables
• Computational Sociolinguistics: A Survey
• Understanding confounding effects in linguistic coordination: an information-theoretic approach
• Natural Language Generation Using Reinforcement Learning with External Rewards
• Guiding Variational Response Generator to Exploit Persona
• Combining Textual Content and Structure to Improve Dialog Similarity
• Quantifying Intimacy in Language
• On the Use of Linguistic Features for the Evaluation of Generative Dialogue Systems
• Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric
• A Multi-Turn Emotionally Engaging Dialog Model
• Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play
• Listening between the Lines: Learning Personal Attributes from Conversations
• Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions
• Speaker Sensitive Response Evaluation Model
• Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation
• Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization
• Building A User-Centric and Content-Driven Socialbot
• Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
• Injecting Hierarchy with U-Net Transformers
• Pchatbot: A Large-Scale Dataset for Personalized Chatbot
• AffectON: Incorporating Affect Into Dialog Generation
• Grounding Conversations with Improvised Dialogues
• Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework
• Data-Efficient Methods for Dialogue Systems
• Learning and Evaluating Sparse Interpretable Sentence Embeddings