A survey of joint intent detection and slot-filling models in natural language understanding

TL;DR

This survey reviews the evolution of joint intent detection and slot filling models in natural language understanding, highlighting key milestones, approaches, datasets, and future directions in the field.

Contribution

It compiles and analyzes past research on joint models for intent detection and slot filling, providing a comprehensive overview and identifying research trends and challenges.

Findings

Joint models outperform independent approaches in accuracy.

Three key milestones identified: intent detection, slot filling, and joint tasks.

Summarizes datasets, evaluation metrics, and performance benchmarks.

Abstract

Intent classification and slot filling are two critical tasks for natural language understanding. Traditionally the two tasks have been deemed to proceed independently. However, more recently, joint models for intent classification and slot filling have achieved state-of-the-art performance, and have proved that there exists a strong relationship between the two tasks. This article is a compilation of past work in natural language understanding, especially joint intent classification and slot filling. We observe three milestones in this research so far: Intent detection to identify the speaker's intention, slot filling to label each word token in the speech/text, and finally, joint intent classification and slot filling tasks. In this article, we describe trends, approaches, issues, data sets, evaluation metrics in intent classification and slot filling. We also discuss representative performance values, describe shared tasks, and provide pointers to future work, as given in prior works. To interpret the state-of-the-art trends, we provide multiple tables that describe and summarise past research along different dimensions, including the types of features, base approaches, and dataset domain used.