Neural Responding Machine for Short-Text Conversation

Abstract

We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it formalizes the generation of response as a decoding process based on the latent representation of the input text, while both encoding and decoding are realized with recurrent neural networks (RNN). The NRM is trained with a large amount of one-round conversation data collected from a microblogging service. Empirical study shows that NRM can generate grammatically correct and content-wise appropriate responses to over 75% of the input text, outperforming state-of-the-arts in the same setting, including retrieval-based and SMT-based models.

accepted as a full paper at ACL 2015

Cited by in corpus (67)

• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Deep Reinforcement Learning for Dialogue Generation
• A Persona-Based Neural Conversation Model
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Smart Reply: Automated Response Suggestion for Email
• Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
• Attention with Intention for a Neural Network Conversation Model
• Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
• Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
• Generative Deep Neural Networks for Dialogue: A Short Review
• Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
• Look, Listen and Learn - A Multimodal LSTM for Speaker Identification
• Plan-And-Write: Towards Better Automatic Storytelling
• Neural Generative Question Answering
• Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings
• Latent Variable Dialogue Models and their Diversity
• Neural Attentive Session-based Recommendation
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
• Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
• Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
• Latent Intention Dialogue Models
• StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation
• Paraphrase Generation with Deep Reinforcement Learning
• From FiLM to Video: Multi-turn Question Answering with Multi-modal Context
• Recurrent Attention Unit
• Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
• Modelling Sentence Pairs with Tree-structured Attentive Encoder
• Neural Personalized Response Generation as Domain Adaptation
• Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
• Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
• Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
• LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues
• Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
• Learning to Start for Sequence to Sequence Architecture
• Hierarchical Memory Networks for Answer Selection on Unknown Words
• Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
• Conditional Generation and Snapshot Learning in Neural Dialogue Systems
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Discovering Dialog Structure Graph for Open-Domain Dialog Generation
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
• ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
• Building Sequential Inference Models for End-to-End Response Selection
• A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots
• Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows
• Learning from Fact-checkers: Analysis and Generation of Fact-checking Language
• Why Do Neural Response Generation Models Prefer Universal Replies?
• Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
• Latent Topic Conversational Models
• Affective Neural Response Generation
• Find the Conversation Killers: a Predictive Study of Thread-ending Posts
• Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms
• Target Guided Emotion Aware Chat Machine
• Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
• Context-Aware Sequence-to-Sequence Models for Conversational Systems
• Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
• Cue-word Driven Neural Response Generation with a Shrinking Vocabulary
• Review-Driven Answer Generation for Product-Related Questions in E-Commerce
• Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study
• A Dataset for Building Code-Mixed Goal Oriented Conversation Systems
• Generating Diverse Translation by Manipulating Multi-Head Attention
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• A Multi-Turn Emotionally Engaging Dialog Model
• Domain-Constrained Advertising Keyword Generation