Open-source multilingual E5 embedding models are trained via contrastive pre-training on 1 billion text pairs and fine-tuning, with an instruction-tuned model matching English SOTA performance.
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multilingual E5 Text Embeddings: A Technical Report
Open-source multilingual E5 embedding models are trained via contrastive pre-training on 1 billion text pairs and fine-tuning, with an instruction-tuned model matching English SOTA performance.