Research paper · 2024-02-08
Multilingual E5 Text Embeddings: A Technical Report
Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei
Abstract
This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023. Three embedding models of different sizes (small / base / large) are provided, offering a balance between the inference efficiency and embedding quality. The training procedure adheres to the English E5 model recipe, involving contrastive pre-training on 1 billion multilingual text pairs, followed by fine-tuning on a combination of labeled datasets. Additionally, we introduce a new instruction-tuned embedding model, whose performance is on par with state-of-the-art, English-only models of similar sizes. Information regarding the model release can be found at https://github.com/microsoft/unilm/tree/master/e5 .
Details
- arXiv identifier
- 2402.05672
- Published
- 2024-02-08
- Authors
- Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei
Models That Cite This Paper
- Described bymultilingual-e5-small
- Described bymultilingual-e5-base
- Described bymultilingual-e5-large
- Described bymultilingual-e5-large-instruct