Enhancing Slot Tagging with Intent Features for Task Oriented Natural Language Understanding using BERT

TL;DR

This paper explores how incorporating intent label features into slot tagging models improves performance in task-oriented natural language understanding, demonstrating significant gains on multiple datasets.

Contribution

It introduces three techniques for leveraging intent features in slot tagging within joint models, enhancing accuracy over existing state-of-the-art methods.

Findings

Improved slot tagging accuracy on SNIPS and ATIS datasets.

Enhanced performance on a large private Bixby dataset.

Intent features significantly boost joint intent and slot detection models.

Abstract

Recent joint intent detection and slot tagging models have seen improved performance when compared to individual models. In many real-world datasets, the slot labels and values have a strong correlation with their intent labels. In such cases, the intent label information may act as a useful feature to the slot tagging model. In this paper, we examine the effect of leveraging intent label features through 3 techniques in the slot tagging task of joint intent and slot detection models. We evaluate our techniques on benchmark spoken language datasets SNIPS and ATIS, as well as over a large private Bixby dataset and observe an improved slot-tagging performance over state-of-the-art models.