Fast and Scalable Expansion of Natural Language Understanding Functionality for Intelligent Agents
This work addresses the time and data-intensive process of developing accurate models for new natural language domains in commercial intelligent agents, though it appears incremental.
The authors tackled the problem of expanding natural language understanding for intelligent agents by proposing efficient deep neural network architectures using transfer learning, which significantly increased accuracy in low-resource settings and enabled rapid model development with less data, as demonstrated on hundreds of new domains.
Fast expansion of natural language functionality of intelligent virtual agents is critical for achieving engaging and informative interactions. However, developing accurate models for new natural language domains is a time and data intensive process. We propose efficient deep neural network architectures that maximally re-use available resources through transfer learning. Our methods are applied for expanding the understanding capabilities of a popular commercial agent and are evaluated on hundreds of new domains, designed by internal or external developers. We demonstrate that our proposed methods significantly increase accuracy in low resource settings and enable rapid development of accurate models with less data.