Fast and Scalable Expansion of Natural Language Understanding Functionality for Intelligent Agents

TL;DR

This paper introduces efficient transfer learning-based neural network architectures that rapidly expand natural language understanding in virtual agents, significantly improving accuracy with less data across numerous domains.

Contribution

It presents novel neural architectures that maximize resource reuse for quick, accurate expansion of language understanding in virtual agents using transfer learning.

Findings

Significantly increased accuracy in low-resource settings

Enabled rapid development of models with less data

Validated on hundreds of new domains

Abstract

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.