MCSE: Multimodal Contrastive Learning of Sentence Embeddings (NAACL 2022)

Paper link: https://aclanthology.org/2022.naacl-main.436/
Github: https://github.com/uds-lsv/MCSE
Author list: Miaoran Zhang, Marius Mosbach, David Adelani, Michael Hedderich, Dietrich Klakow

Model Details

base model: roberta-base
training data: Wiki1M + Flicker30k

Evaluation Results

STS12	STS13	STS14	STS15	STS16	STSBenchmark	SICKRelatedness	Avg.
71.74	82.60	75.67	84.49	80.74	81.52	72.30	78.44

Downloads last month: 2

Safetensors

Model size

125M params

Tensor type

F32

Feature Extraction

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.