Texts

MASSIVE

Introduced by FitzGerald et al. in MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages

MASSIVE is a parallel dataset of > 1M utterances across 51 languages with annotations for the Natural Language Understanding tasks of intent prediction and slot annotation. Utterances span 60 intents and include 55 slot types. MASSIVE was created by localizing the SLURP dataset, composed of general Intelligent Voice Assistant single-shot interactions.

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Text Classification	MASSIVE	distilbert-base-Massive-intent
intent-classification	MASSIVE	bert-base-uncased-amazon-massive-intent
Zero-Shot Intent Classification	MASSIVE	XLM-R Base
Zero-shot Slot Filling	MASSIVE	XLM-R Base
Intent Classification and Slot Filling	MASSIVE	XLM-R Base
Zero-Shot Intent Classification and Slot Filling	MASSIVE	XLM-R Base
Intent Classification	MASSIVE	mT5 Base
Slot Filling	MASSIVE	XLM-R Base
text-classification	MASSIVE	xlm-r-base-amazon-massive-domain
slot-filling	MASSIVE	xlm-r-base-amazon-massive-slot