MultiNLI (Multi-Genre Natural Language Inference)

Introduced by Williams et al. in A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference

The Multi-Genre Natural Language Inference (MultiNLI) dataset has 433K sentence pairs. Its size and mode of collection are modeled closely like SNLI. MultiNLI offers ten distinct genres (Face-to-face, Telephone, 9/11, Travel, Letters, Oxford University Press, Slate, Verbatim, Goverment and Fiction) of written and spoken English data. There are matched dev/test sets which are derived from the same sources as those in the training set, and mismatched sets which do not closely resemble any seen at training time.

Source: Semantic Sentence Matching with Densely-connectedRecurrent and Co-attentive Information

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Natural Language Inference	MultiNLI	Turing NLR v5 XXL 5.4B
Natural Language Inference	MultiNLI Dev	TinyBERT-6 67M
MNLI-mm	MNLI-mm	asi/albert-act-base
MNLI-m	MNLI-m	asi/albert-act-base
Text Generation	MNLI	bloom
Text Generation	mnli_mismatched	bloom
Faithfulness Critic	MNLI	roberta-large-faithcritic
Natural Language Inference	multi_nli	MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli