Multilingual E5 Text Embeddings: A Technical Report
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911773617029120 |
|---|---|
| author | Wang, Liang Yang, Nan Huang, Xiaolong Yang, Linjun Majumder, Rangan Wei, Furu |
| author_facet | Wang, Liang Yang, Nan Huang, Xiaolong Yang, Linjun Majumder, Rangan Wei, Furu |
| contents | 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 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05672 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multilingual E5 Text Embeddings: A Technical Report Wang, Liang Yang, Nan Huang, Xiaolong Yang, Linjun Majumder, Rangan Wei, Furu Computation and Language Information Retrieval 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 . |
| title | Multilingual E5 Text Embeddings: A Technical Report |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2402.05672 |