Dataset composed of online banking queries annotated with their corresponding intents.
BANKING77 dataset provides a very fine-grained set of intents in a banking domain. It comprises 13,083 customer service queries labeled with 77 intents. It focuses on fine-grained single-domain intent detection.
Variants: BANKING77, BANKING77 10-shot, BANKING77 5-shot
This dataset is used in 3 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Intent Detection | OCaTS (kNN-GPT-4) | Cache me if you Can: … | 2023-10-20 |
| Intent Detection | RoBERTa-Large + ICDA | Selective In-Context Data Augmentation for … | 2023-02-10 |
| Text Classification | 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: