A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

Abstract

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.

arXiv commentA. Sordoni, M. Galley, M. Auli, C. Brockett, Y. Ji, M. Mitchell, J.-Y. Nie, J. Gao, B. Dolan. 2015. A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. In Proc. of NAACL-HLT. Pages 196-205

Cited by in corpus (60)

• Recent Trends in Deep Learning Based Natural Language Processing
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Mutual Information and Diverse Decoding Improve Neural Machine Translation
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Neural Models for Information Retrieval
• Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model
• Context-aware Natural Language Generation with Recurrent Neural Networks
• LSTM based Conversation Models
• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
• Learning to Decode for Future Success
• EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems
• Recent advances in conversational NLP : Towards the standardization of Chatbot building
• Deep Learning Based Chatbot Models
• A Neural Transducer
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• A Conditional Variational Framework for Dialog Generation
• Toward Continual Learning for Conversational Agents
• Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• MojiTalk: Generating Emotional Responses at Scale
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• RubyStar: A Non-Task-Oriented Mixture Model Dialog System
• Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Deep Active Learning for Dialogue Generation
• Learning to Start for Sequence to Sequence Architecture
• Natural Language Generation with Neural Variational Models
• End-to-end Adversarial Learning for Generative Conversational Agents
• Link Prediction using Embedded Knowledge Graphs
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems
• Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
• A Large-Scale Chinese Short-Text Conversation Dataset
• OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
• Why are Sequence-to-Sequence Models So Dull? Understanding the Low-Diversity Problem of Chatbots
• What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
• Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
• Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-Play
• Knowledge-based end-to-end memory networks
• The RLLChatbot: a solution to the ConvAI challenge
• How Do Neural Sequence Models Generalize? Local and Global Context Cues for Out-of-Distribution Prediction
• Predict and Use Latent Patterns for Short-Text Conversation
• Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
• Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
• Game-Based Video-Context Dialogue
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions
• Candidates vs. Noises Estimation for Large Multi-Class Classification Problem