Personalizing Dialogue Agents: I have a dog, do you have pets too?

Abstract

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i) condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• A Neural Conversational Model
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Deep Reinforcement Learning for Dialogue Generation
• A Deep Reinforcement Learning Chatbot
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• A Persona-Based Neural Conversation Model
• StarSpace: Embed All The Things!
• Reading Wikipedia to Answer Open-Domain Questions
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Generative Deep Neural Networks for Dialogue: A Short Review
• Personalization in Goal-Oriented Dialog
• Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems

Cited by in corpus (86)

• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Towards a Human-like Open-Domain Chatbot
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
• Personalized Dialogue Generation with Diversified Traits
• Ensemble-Based Deep Reinforcement Learning for Chatbots
• ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons
• Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
• EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Training Millions of Personalized Dialogue Agents
• PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
• STAR: A Schema-Guided Dialog Dataset for Transfer Learning
• Coreference Resolution as Query-based Span Prediction
• Towards Conversational Recommendation over Multi-Type Dialogs
• Gunrock 2.0: A User Adaptive Social Conversational System
• A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Improving Background Based Conversation with Context-aware Knowledge Pre-selection
• Retrieve and Refine: Improved Sequence Generation Models For Dialogue
• Auditing Data Provenance in Text-Generation Models
• End-to-End Trainable Non-Collaborative Dialog System
• Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data
• Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
• Non-Autoregressive Neural Dialogue Generation
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Defending Against Backdoor Attacks in Natural Language Generation
• A Dataset for Document Grounded Conversations
• Domain Adaptive Text Style Transfer
• Open Korean Corpora: A Practical Report
• Evaluating Empathetic Chatbots in Customer Service Settings
• "My Way of Telling a Story": Persona based Grounded Story Generation
• I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents
• Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
• Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems
• Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue
• Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges
• Dialogue Response Ranking Training with Large-Scale Human Feedback Data
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• DLGNet: A Transformer-based Model for Dialogue Response Generation
• Proto: A Neural Cocktail for Generating Appealing Conversations
• Interview: A Large-Scale Open-Source Corpus of Media Dialog
• Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
• How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
• A Large-Scale Chinese Short-Text Conversation Dataset
• Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
• A Batch Normalized Inference Network Keeps the KL Vanishing Away
• Regularizing Dialogue Generation by Imitating Implicit Scenarios
• Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm
• Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
• Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness
• Learning Personalized End-to-End Goal-Oriented Dialog
• Assessing Dialogue Systems with Distribution Distances
• Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner
• Generating Personalized Recipes from Historical User Preferences
• Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models
• Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking
• Generating Dialogue Responses from a Semantic Latent Space
• The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity
• Language Model Evaluation in Open-ended Text Generation
• Structural and Functional Decomposition for Personality Image Captioning in a Communication Game
• Group-wise Contrastive Learning for Neural Dialogue Generation
• Content Selection Network for Document-grounded Retrieval-based Chatbots
• Adversarial Bootstrapping for Dialogue Model Training
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• Interactive Storytelling for Children: A Case-study of Design and Development Considerations for Ethical Conversational AI
• Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation
• Adversarial Semantic Collisions
• Keyword-Guided Neural Conversational Model
• Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions
• Controlled Language and Baby Turing Test for General Conversational Intelligence
• Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• Commonsense-Focused Dialogues for Response Generation: An Empirical Study
• Conversational Semantic Role Labeling
• Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
• A Corpus of Controlled Opinionated and Knowledgeable Movie Discussions for Training Neural Conversation Models
• POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling
• Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
• Viola: A Topic Agnostic Generate-and-Rank Dialogue System
• A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions
• A Gated Self-attention Memory Network for Answer Selection
• Injecting Hierarchy with U-Net Transformers