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
Variants: CLINC150, clinc_oos, CLINC150 5-shot, CLINC150 10-shot
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Intent Detection | RoBERTa-Large + ICDA | Selective In-Context Data Augmentation for … | 2023-02-10 |
| Open Intent Discovery | DeepAligned | Discovering New Intents with Deep … | 2020-12-16 |
Recent papers with results on this dataset: