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

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