Topic Aware Neural Response Generation

Abstract

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model utilizes topics to simulate prior knowledge of human that guides them to form informative and interesting responses in conversation, and leverages the topic information in generation by a joint attention mechanism and a biased generation probability. The joint attention mechanism summarizes the hidden vectors of an input message as context vectors by message attention, synthesizes topic vectors by topic attention from the topic words of the message obtained from a pre-trained LDA model, and let these vectors jointly affect the generation of words in decoding. To increase the possibility of topic words appearing in responses, the model modifies the generation probability of topic words by adding an extra probability item to bias the overall distribution. Empirical study on both automatic evaluation metrics and human annotations shows that TA-Seq2Seq can generate more informative and interesting responses, and significantly outperform the-state-of-the-art response generation models.

Cited by in corpus (98)

• Towards a Human-like Open-Domain Chatbot
• A Survey of Knowledge-Enhanced Text Generation
• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• If I Hear You Correctly: Building and Evaluating Interview Chatbots with Active Listening Skills
• Low-Resource Knowledge-Grounded Dialogue Generation
• Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
• Zero-Resource Knowledge-Grounded Dialogue Generation
• Challenges in Building Intelligent Open-domain Dialog Systems
• Deep Learning Based Chatbot Models
• Generate Natural Language Explanations for Recommendation
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• What makes a good conversation? How controllable attributes affect human judgments
• Towards a Continuous Knowledge Learning Engine for Chatbots
• Lifelong and Interactive Learning of Factual Knowledge in Dialogues
• CPM: A Large-scale Generative Chinese Pre-trained Language Model
• Domain Aware Neural Dialog System
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Towards Topic-Guided Conversational Recommender System
• Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
• Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
• Steering Output Style and Topic in Neural Response Generation
• Lifelong Knowledge Learning in Rule-based Dialogue Systems
• Non-Autoregressive Neural Dialogue Generation
• Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs
• DAL: Dual Adversarial Learning for Dialogue Generation
• Adaptive Parameterization for Neural Dialogue Generation
• Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
• RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models
• ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
• TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System
• Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems
• RefNet: A Reference-aware Network for Background Based Conversation
• Meaningful Answer Generation of E-Commerce Question-Answering
• Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
• Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
• A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation
• Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots
• Retrieval-Enhanced Adversarial Training for Neural Response Generation
• Discovering Dialog Structure Graph for Open-Domain Dialog Generation
• Conditional Text Generation for Harmonious Human-Machine Interaction
• Neural Response Generation with Meta-Words
• Why Do Neural Response Generation Models Prefer Universal Replies?
• Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
• Theme-aware generation model for chinese lyrics
• Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
• The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection
• Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
• ARAML: A Stable Adversarial Training Framework for Text Generation
• Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication
• Affective Neural Response Generation
• Fine-Grained Sentence Functions for Short-Text Conversation
• Enhancing Dialogue Generation via Multi-Level Contrastive Learning
• Regularizing Dialogue Generation by Imitating Implicit Scenarios
• A Discrete CVAE for Response Generation on Short-Text Conversation
• Topic-Aware Multi-turn Dialogue Modeling
• Target Guided Emotion Aware Chat Machine
• A Scalable Chatbot Platform Leveraging Online Community Posts: A Proof-of-Concept Study
• A Manually Annotated Chinese Corpus for Non-task-oriented Dialogue Systems
• Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization
• Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight
• Group-wise Contrastive Learning for Neural Dialogue Generation
• Condition-Transforming Variational AutoEncoder for Conversation Response Generation
• Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning
• Content Selection Network for Document-grounded Retrieval-based Chatbots
• Dialogue-oriented Pre-training
• Cue-word Driven Neural Response Generation with a Shrinking Vocabulary
• Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job
• Guiding Variational Response Generator to Exploit Persona
• Multi-Source Pointer Network for Product Title Summarization
• A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation
• Query-Variant Advertisement Text Generation with Association Knowledge
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• A Multi-Turn Emotionally Engaging Dialog Model
• Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness
• DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
• Generating Pertinent and Diversified Comments with Topic-aware Pointer-Generator Networks
• Counterfactual Off-Policy Training for Neural Response Generation
• Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering
• HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation
• Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network
• Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
• Unsupervised Context Rewriting for Open Domain Conversation
• Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization
• Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
• A Dataset of General-Purpose Rebuttal
• ScriptWriter: Narrative-Guided Script Generation
• Pchatbot: A Large-Scale Dataset for Personalized Chatbot
• Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
• An Emotion-controlled Dialog Response Generation Model with Dynamic Vocabulary
• Conversational Semantic Role Labeling
• Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
• Generating Informative Dialogue Responses with Keywords-Guided Networks
• Focus-Constrained Attention Mechanism for CVAE-based Response Generation
• Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions