Attention with Intention for a Neural Network Conversation Model

Abstract

In a conversation or a dialogue process, attention and intention play intrinsic roles. This paper proposes a neural network based approach that models the attention and intention processes. It essentially consists of three recurrent networks. The encoder network is a word-level model representing source side sentences. The intention network is a recurrent network that models the dynamics of the intention process. The decoder network is a recurrent network produces responses to the input from the source side. It is a language model that is dependent on the intention and has an attention mechanism to attend to particular source side words, when predicting a symbol in the response. The model is trained end-to-end without labeling data. Experiments show that this model generates natural responses to user inputs.

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Listen, Attend and Spell
• Neural Responding Machine for Short-Text Conversation
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
• Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion
• Depth-Gated LSTM

Cited by in corpus (23)

• Deep Reinforcement Learning for Dialogue Generation
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Adversarial Learning for Neural Dialogue Generation
• A Persona-Based Neural Conversation Model
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
• Deep Learning Based Chatbot Models
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• A Conditional Variational Framework for Dialog Generation
• Backward and Forward Language Modeling for Constrained Sentence Generation
• Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
• Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History
• Neural Contextual Conversation Learning with Labeled Question-Answering Pairs
• Deep Active Learning for Dialogue Generation
• Deep Reinforcement Learning for Conversational AI
• Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
• Towards Automatic Generation of Entertaining Dialogues in Chinese Crosstalks
• Paying Attention to Attention: Highlighting Influential Samples in Sequential Analysis
• SEntNet: Source-aware Recurrent Entity Network for Dialogue Response Selection
• MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
• A Dataset for Building Code-Mixed Goal Oriented Conversation Systems
• Automatic Evaluation of Neural Personality-based Chatbots