# Cross-Lingual Retrieval

This is a text reranking model based on 0.5B parameters, supporting multilingual text ranking tasks.

A bilingual sentence transformer model fine-tuned based on FacebookAI/xlm-roberta-large, supporting semantic text similarity calculation for Arabic and English.

BCEmbedding is a bilingual and cross-lingual embedding model library developed by NetEase Youdao, including EmbeddingModel (semantic vector generation) and RerankerModel (result reranking). As a core component of Youdao's Retrieval-Augmented Generation (RAG) system, it has been successfully applied to open-source projects like QAnything and products such as Youdao Speed Reading and Youdao Translation.

Multilingual sentence embedding model supporting text similarity computation and semantic search for 50+ languages

A Czech-English semantic embedding model fine-tuned with SimCSE objective, based on Seznam/dist-mpnet-paracrawl-cs-en

A distilled model based on BERT-small architecture, specifically designed for Czech-English semantic embedding

A locally sparse global version based on intfloat/multilingual-e5-small, supporting multilingual text embedding models with approximately 4k tokens

A multilingual sentence embedding model based on sentence-transformers, specially optimized for Bengali, suitable for semantic similarity calculation and clustering analysis

This is a sentence transformer model based on distilled BERT, supporting Korean and English for sentence similarity calculation and feature extraction.

This is a sentence transformer model based on XLM-RoBERTa, which maps text to a 768-dimensional vector space, suitable for tasks such as semantic search and sentence similarity calculation.