Attention over Parameters for Dialogue Systems
arXiv:2001.01871
Abstract
Dialogue systems require a great deal of different but complementary expertise to assist, inform, and entertain humans. For example, different domains (e.g., restaurant reservation, train ticket booking) of goal-oriented dialogue systems can be viewed as different skills, and so does ordinary chatting abilities of chit-chat dialogue systems. In this paper, we propose to learn a dialogue system that independently parameterizes different dialogue skills, and learns to select and combine each of them through Attention over Parameters (AoP). The experimental results show that this approach achieves competitive performance on a combined dataset of MultiWOZ, In-Car Assistant, and Persona-Chat. Finally, we demonstrate that each dialogue skill is effectively learned and can be combined with other skills to produce selective responses.
NeurIPS Conversational AI Workshops (Best Paper Award)
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- Natural Language Processing (almost) from Scratch
- An Overview of Multi-Task Learning in Deep Neural Networks
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- A Neural Conversational Model
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Adaptive Computation Time for Recurrent Neural Networks
- The Natural Language Decathlon: Multitask Learning as Question Answering
- TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
- One Model To Learn Them All
- Nonlinear Models Using Dirichlet Process Mixtures
- Conditional Computation in Neural Networks for faster models
- Generative Deep Neural Networks for Dialogue: A Short Review
- Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
- CAiRE: An Empathetic Neural Chatbot
- Dialogue Natural Language Inference