CLINC150

Introduced by Larson et al. in An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction

This dataset is for evaluating the performance of intent classification systems in the presence of "out-of-scope" queries, i.e., queries that do not fall into any of the system-supported intent classes. The dataset includes both in-scope and out-of-scope data.

Source: CLINC150

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Text Classification	clinc_oos	distilbert-base-uncased-distilled-clinc
Open Intent Discovery	CLINC150	DSSCC
Intent Detection	CLINC150	RoBERTa-Large + ICDA
Intent Detection	CLINC150 5-shot	RoBERTa-Large + ICDA
Intent Detection	CLINC150 10-shot	RoBERTa-Large + ICDA