A Persona-Based Neural Conversation Model

Abstract

We present persona-based models for handling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed embeddings that capture individual characteristics such as background information and speaking style. A dyadic speaker-addressee model captures properties of interactions between two interlocutors. Our models yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models, with similar gains in speaker consistency as measured by human judges.

Accepted for publication at ACL 2016

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• A Neural Conversational Model
• Neural Responding Machine for Short-Text Conversation
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Attention with Intention for a Neural Network Conversation Model
• deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

Cited by in corpus (87)

• Recent Trends in Deep Learning Based Natural Language Processing
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Deep Reinforcement Learning for Dialogue Generation
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• Style Transfer as Unsupervised Machine Translation
• Personalized Dialogue Generation with Diversified Traits
• Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
• One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles
• Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
• Personalization in Goal-Oriented Dialog
• LSTM based Conversation Models
• Controlling Output Length in Neural Encoder-Decoders
• Topic-based Evaluation for Conversational Bots
• Deep Learning Based Chatbot Models
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Latent Variable Dialogue Models and their Diversity
• Style Transfer in Text: Exploration and Evaluation
• Training Millions of Personalized Dialogue Agents
• Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
• A Hybrid Retrieval-Generation Neural Conversation Model
• Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
• Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems
• Coreference Resolution as Query-based Span Prediction
• Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
• Building a Chatbot on a Closed Domain using RASA
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction
• Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
• Sentiment Transfer using Seq2Seq Adversarial Autoencoders
• Natural Language Generation with Neural Variational Models
• Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
• Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
• End-to-end Adversarial Learning for Generative Conversational Agents
• I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents
• Deploying Lifelong Open-Domain Dialogue Learning
• Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
• Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges
• The Rapidly Changing Landscape of Conversational Agents
• Deep Reinforcement Learning for Conversational AI
• Automatic Conditional Generation of Personalized Social Media Short Texts
• SparCE: Sparsity aware General Purpose Core Extensions to Accelerate Deep Neural Networks
• Why Do Neural Response Generation Models Prefer Universal Replies?
• A Large-Scale Chinese Short-Text Conversation Dataset
• Polite Dialogue Generation Without Parallel Data
• Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
• Consistency and Coherency Enhanced Story Generation
• Learning Personalized End-to-End Goal-Oriented Dialog
• Low-Rank RNN Adaptation for Context-Aware Language Modeling
• Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
• Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight
• Diversifying Dialogue Generation with Non-Conversational Text
• Improving Context Aware Language Models
• Target Guided Emotion Aware Chat Machine
• SEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection
• When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
• Investigation of Sentiment Controllable Chatbot
• Ivermectin and Doxycycline Combination as a Promising Drug Candidate Against SARS-CoV-2 Infection: A Computational Study
• Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
• Predicting the time-evolution of multi-physics systems with sequence-to-sequence models
• Adversarial Learning of Task-Oriented Neural Dialog Models
• Context-Aware Sequence-to-Sequence Models for Conversational Systems
• A Multi-Turn Emotionally Engaging Dialog Model
• A Face-to-Face Neural Conversation Model
• Neural MultiVoice Models for Expressing Novel Personalities in Dialog
• Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification
• Pchatbot: A Large-Scale Dataset for Personalized Chatbot
• Automatically Select Emotion for Response via Personality-affected Emotion Transition
• AI Stories: An Interactive Narrative System for Children
• An Empirical Study of Extrapolation in Text Generation with Scalar Control
• Memory-Augmented Recurrent Networks for Dialogue Coherence
• 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
• Automatic Generation of Personalized Comment Based on User Profile
• A Base Camp for Scaling AI
• Game-Based Video-Context Dialogue
• Improving Search through A3C Reinforcement Learning based Conversational Agent