Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
Explore this paper's citation graph
Summary
The recently proposed hierarchical recurrent encoder-decoder neural network is extended to the dialogue domain, and it is demonstrated that this model is competitive with state-of-the-art neural language models and back-off n-gram models.
- Type
- preprint
- Published
- 2015-07-17
- Cited by
- 1,815
- References
- 54
- Access
- Open access
- OpenAlex
- https://openalex.org/W889023230
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:6126582
Keywords
Generative grammar, Computer science, Bootstrapping (finance), Word (group theory), Artificial intelligence
References
- Data-Driven Response Generation in Social Media
- Recurrent neural network based language model
- Chatbots: Are they Really Useful?
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- Spontaneity reloaded: American face-to-face and movie conversation compared
- A Neural Conversational Model
- Theano: new features and speed improvements
- Unsupervised Modeling of Twitter Conversations
- Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
- LSTM: A Search Space Odyssey
- Sequence Transduction with Recurrent Neural Networks
- Show and tell: A neural image caption generator
- POMDP-Based Statistical Spoken Dialog Systems: A Review
- Tell me when and why to do it! Run-time planner model updates via natural language instruction
- On-line policy optimisation of Bayesian spoken dialogue systems via human interaction
- A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion
- Abductive understanding of dialogues about joint activities
- Long Short-Term Memory
- Hierarchical Recurrent Neural Networks for Long-Term Dependencies
- Deep Neural Network Approach for the Dialog State Tracking Challenge
Cited by
- Semisupervised Text Classification by Variational Autoencoder
- Survey on evaluation methods for dialogue systems
- Transitive Transfer Learning
- Neural Generative Question Answering
- Mutual Information and Diverse Decoding Improve Neural Machine Translation
- Learning Distributed Representations of Sentences from Unlabelled Data
- Semi-supervised Variational Autoencoders for Sequence Classification
- A Persona-Based Neural Conversation Model
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves
- Using Sentence-Level LSTM Language Models for Script Inference
- LSTM-Based Mixture-of-Experts for Knowledge-Aware Dialogues
- Compositional Sentence Representation from Character Within Large Context Text
- Review of state-of-the-arts in artificial intelligence with application to AI safety problem
- Smart Reply: Automated Response Suggestion for Email
- On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
- On the Evaluation of Dialogue Systems with Next Utterance Classification
- A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
- Deep Reinforcement Learning for Dialogue Generation
- An Attentional Neural Conversation Model with Improved Specificity
Related papers
- A Neural Conversational Model
- Long Short-Term Memory
- Data-Driven Response Generation in Social Media
- Deep Reinforcement Learning for Dialogue Generation
- Bleu: a Method for Automatic Evaluation of Machine Translation
- POMDP-Based Statistical Spoken Dialog Systems: A Review
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- Neural Responding Machine for Short-Text Conversation