Technical Program

Paper Detail

Presentation #7
Location:Kallirhoe Hall
Session Time:Thursday, December 20, 10:00 - 12:00
Presentation Time:Thursday, December 20, 10:00 - 12:00
Presentation: Poster
Topic: Spoken dialog systems:
Paper Title: Accumulating Conversational Skills using Continual Learning
Authors: Sungjin Lee, Microsoft Research, United States
Abstract: While neural conversational models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, training neural models from scratch requires an enormous amount of data. If pre-trained models can be reused when they have many things in common with a new task, we can significantly cut down the amount of required data. To achieve this goal, we adopt a neural continual learning algorithm to allow a conversational agent to accumulate skills across different tasks in a data-efficient way. We present preliminary results on conversational skill accumulation on multiple task-oriented domains.