BANKING77

English banking intent classification of 13,083 customer-service queries into 77 intents; HELM scores generated labels by exact match.

Also known as: BANKING 77, PolyAI BANKING77

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorydomain
Subcategoryfine-grained English banking intent classification (77 labels)
Page statusactive
Metricexact match of the intent name (HELM); accuracy in the original paper
Directionhigher_is_better
Unit%
Dataset size13083
Dataset licenceCC-BY-4.0
PublisherPolyAI Limited

What it measures

BANKING77 asks a model to map a short English customer-service utterance to one of 77 fine-grained banking intents (card arrival, failed top-up, reverted transfer, and so on). PolyAI released it as a single-domain contrast to coarser multi-domain sets such as HWU64 and CLINC150. Overlapping intents are deliberate: the model must tell failed top-up from reverted top-up, not just "banking" from "travel".

Task format

Single-label text classification. HELM presents the query and generates a label string, then scores quasi-exact / exact match against the canonical intent name. The original paper instead trains a classifier on frozen sentence embeddings and reports accuracy.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub