An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction

TL;DR

This paper introduces a new dataset for intent classification in task-oriented dialog systems that includes out-of-scope queries, highlighting the challenge of detecting queries outside supported intents and providing a benchmark for future research.

Contribution

It presents a comprehensive dataset with out-of-scope queries across 150 intents and evaluates classifiers, addressing a key gap in realistic intent detection benchmarking.

Findings

Classifiers perform well on in-scope intent classification.

Detection of out-of-scope queries remains challenging.

The dataset enables more realistic benchmarking of dialog systems.

Abstract

Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover every example. We introduce a new dataset that includes queries that are out-of-scope---i.e., queries that do not fall into any of the system's supported intents. This poses a new challenge because models cannot assume that every query at inference time belongs to a system-supported intent class. Our dataset also covers 150 intent classes over 10 domains, capturing the breadth that a production task-oriented agent must handle. We evaluate a range of benchmark classifiers on our dataset along with several different out-of-scope identification schemes. We find that while the classifiers perform well on in-scope intent classification, they struggle to identify out-of-scope queries. Our dataset and evaluation fill an important gap in the field, offering a way of more rigorously and realistically benchmarking text classification in task-driven dialog systems.