SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU

arXiv:2311.09502v2 Announce Type: replace
Abstract: Task-oriented dialogue (ToD) systems help users execute well-defined tasks across a variety of domains (e.g., $\textit{flight booking}$ or $\textit{food ordering}$), with their Natural Language Understanding (NLU) components being dedicated to the analysis of user utterances, predicting users' intents ($\textit{Intent Detection}$, ID) and extracting values for informational slots ($\textit{Value Extraction}$, VE). In most domains, labelled NLU data is scarce, making sample-efficient learning -- enabled with effective transfer paradigms -- paramount. In this work, we introduce SQATIN, …

abstract analysis arxiv components cs.cl detection dialogue domains food intent detection language language understanding natural natural language nlu question question answering systems tasks type understanding values