Domain Adaptation of Recurrent Neural Networks for Natural Language Understanding

TL;DR

This paper presents a multi-task learning approach for recurrent neural networks to improve natural language understanding across multiple domains, reducing data requirements and supporting open vocabulary generalization.

Contribution

It introduces a scalable multi-task model that leverages shared patterns for domain adaptation and open vocabulary handling in slot filling tasks.

Findings

Enhanced performance with less training data

Effective domain adaptation demonstrated on new dataset

Supports generalization to unseen words

Abstract

The goal of this paper is to use multi-task learning to efficiently scale slot filling models for natural language understanding to handle multiple target tasks or domains. The key to scalability is reducing the amount of training data needed to learn a model for a new task. The proposed multi-task model delivers better performance with less data by leveraging patterns that it learns from the other tasks. The approach supports an open vocabulary, which allows the models to generalize to unseen words, which is particularly important when very little training data is used. A newly collected crowd-sourced data set, covering four different domains, is used to demonstrate the effectiveness of the domain adaptation and open vocabulary techniques.