French - document - embedding open - source model - Free support for French - English sentence similarity calculation and feature extraction

French Document Embedding

Developed by dangvantuan

A multilingual sentence embedding model based on the sentence-transformers library, supporting sentence similarity calculation and feature extraction for French and English.

Text Embedding

Transformers

Supports Multiple LanguagesOpen Source License:Apache-2.0 #French-English Sentence Embeddings #Educational Content Clustering #Multilingual Retrieval Optimization

Downloads 6,028

Release Time : 8/16/2024

Model Overview

This model specializes in generating high-quality sentence embeddings for calculating semantic similarity between sentences, supporting both French and English. Suitable for tasks such as clustering, reranking, and retrieval.

Model Features

Multilingual Support

Supports sentence embedding generation for French and English, suitable for multilingual scenarios.

High-Performance Clustering

Achieves a v_measure score of 59.69 on the AlloProfClusteringP2P task, demonstrating excellent performance.

Precision Reranking

Achieves a map value of 73.52 and an mrr value of 74.86 on the AlloprofReranking task, showing significant reranking effectiveness.

Model Capabilities

Sentence similarity calculation

Feature extraction

Text clustering

Retrieval result reranking

Multilingual processing

Use Cases

Education

Educational Content Clustering

Automatically clusters educational-related text content for easier content management and retrieval.

Achieves a v_measure of 59.69 on the AlloProfClusteringP2P task.

Information Retrieval

Retrieval Result Reranking

Semantically reranks search engine results to improve relevance.

Achieves a map value of 73.52 on the AlloprofReranking task.

🚀 Sentence-Transformers

Sentence-Transformers is a library for state-of-the-art sentence, text and image embeddings. This model is designed for sentence similarity tasks and supports multiple languages including French and English.

📚 Documentation

Model Information

Property	Details
Library Name	sentence-transformers
Pipeline Tag	sentence-similarity
Tags	sentence-transformers, feature-extraction, sentence-similarity, transformers, french, english, sentence-embedding, mteb

Model Results

Model Name: 7eff199d41ff669fad99d83cad9249c393c3f14b

Clustering - MTEB AlloProfClusteringP2P

Task Type: Clustering
Dataset:
- Type: lyon-nlp/alloprof
- Name: MTEB AlloProfClusteringP2P
- Config: default
- Split: test
- Revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
Metrics:
- v_measure: 59.69196295449414
- v_measures: [0.6355772777559684, 0.4980707615440343, 0.5851538838323186, 0.6567709175938427, 0.5712405288636999]

Clustering - MTEB AlloProfClusteringS2S

Task Type: Clustering
Dataset:
- Type: lyon-nlp/alloprof
- Name: MTEB AlloProfClusteringS2S
- Config: default
- Split: test
- Revision: 392ba3f5bcc8c51f578786c1fc3dae648662cb9b
Metrics:
- v_measure: 45.607106996926426
- v_measures: [0.45846869913649535, 0.42657120373128293, 0.45507356125930876, 0.4258913306353704, 0.4779122207000794]

Reranking - MTEB AlloprofReranking

Task Type: Reranking
Dataset:
- Type: lyon-nlp/mteb-fr-reranking-alloprof-s2p
- Name: MTEB AlloprofReranking
- Config: default
- Split: test
- Revision: 65393d0d7a08a10b4e348135e824f385d420b0fd
Metrics:
- map: 73.51836428087765
- mrr: 74.8550285111166
- nAUC_map_diff1: 56.006169898728466
- nAUC_map_max: 27.886037223407506
- nAUC_mrr_diff1: 56.68072778248672
- nAUC_mrr_max: 29.362681962243276

Retrieval - MTEB AlloprofRetrieval

Task Type: Retrieval
Dataset:
- Type: lyon-nlp/alloprof
- Name: MTEB AlloprofRetrieval
- Config: default
- Split: test
- Revision: fcf295ea64c750f41fadbaa37b9b861558e1bfbd
Metrics: (A large number of metrics are provided, please refer to the original data for details)

Classification - MTEB AmazonReviewsClassification (fr)

Task Type: Classification
Dataset:
- Type: mteb/amazon_reviews_multi
- Name: MTEB AmazonReviewsClassification (fr)
- Config: fr
- Split: test
- Revision: 1399c76144fd37290681b995c656ef9b2e06e26d
Metrics:
- accuracy: 39.892
- f1: 38.38126304364462
- f1_weighted: 38.38126304364462

Retrieval - MTEB BSARDRetrieval

Task Type: Retrieval
Dataset:
- Type: maastrichtlawtech/bsard
- Name: MTEB BSARDRetrieval
- Config: default
- Split: test
- Revision: 5effa1b9b5fa3b0f9e12523e6e43e5f86a6e6d59
Metrics: (A large number of metrics are provided, please refer to the original data for details)

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご