Generative Deep Neural Networks for Dialogue: A Short Review
arXiv:1611.06216
Abstract
Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue response generation. The hope is that such models will be able to leverage massive amounts of data to learn meaningful natural language representations and response generation strategies, while requiring a minimum amount of domain knowledge and hand-crafting. An important challenge is to develop models that can effectively incorporate dialogue context and generate meaningful and diverse responses. In support of this goal, we review recently proposed models based on generative encoder-decoder neural network architectures, and show that these models have better ability to incorporate long-term dialogue history, to model uncertainty and ambiguity in dialogue, and to generate responses with high-level compositional structure.
6 pages, 1 figure, 3 tables; NIPS 2016 workshop on Learning Methods for Dialogue
References in corpus (2)
Cited by in corpus (12)
- Emergent Multi-Agent Communication in the Deep Learning Era
- Attention over Parameters for Dialogue Systems
- Data Distillation for Controlling Specificity in Dialogue Generation
- Robust Conversational AI with Grounded Text Generation
- Non-Autoregressive Neural Dialogue Generation
- A Repository of Conversational Datasets
- Transfer Learning for British Sign Language Modelling
- Teaching Machines to Converse
- Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation
- Is this Dialogue Coherent? Learning from Dialogue Acts and Entities
- Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge
- Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations