Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey

TL;DR

This survey reviews recent neural network approaches for slot filling and intent classification in task-oriented dialogue systems, highlighting architectures, advancements, and ongoing challenges in natural language understanding.

Contribution

It provides a comprehensive overview of neural models, including independent, joint, and transfer learning architectures, for improving dialogue system understanding.

Findings

Neural models have rapidly evolved for SF and IC tasks.

Joint models leverage mutual benefits of SF and IC.

Transfer learning enables domain adaptation in dialogue systems.

Abstract

In recent years, fostered by deep learning technologies and by the high demand for conversational AI, various approaches have been proposed that address the capacity to elicit and understand user's needs in task-oriented dialogue systems. We focus on two core tasks, slot filling (SF) and intent classification (IC), and survey how neural-based models have rapidly evolved to address natural language understanding in dialogue systems. We introduce three neural architectures: independent model, which model SF and IC separately, joint models, which exploit the mutual benefit of the two tasks simultaneously, and transfer learning models, that scale the model to new domains. We discuss the current state of the research in SF and IC and highlight challenges that still require attention.