# Dense passage retrieval

A dual-encoder retrieval model for the medical field, capable of processing Korean-English mixed medical records.

This is a dense single-vector dual-encoder model for French, suitable for semantic search. The model maps queries and passages to 384-dimensional dense vectors and calculates relevance through cosine similarity.

This is a dense single-vector dual-encoder model for French, designed for semantic search. The model maps queries and passages to 768-dimensional dense vectors and calculates relevance through cosine similarity.

This is a dense single-vector dual encoder model for French, suitable for semantic search. The model maps queries and passages to 768-dimensional dense vectors and calculates relevance through cosine similarity.

This is a dense single-vector dual-encoder model for French, suitable for semantic search tasks.

DPR (Dense Passage Retrieval) is a tool and model for open-domain question answering research. This model is a BERT-based question encoder trained on the Natural Questions (NQ) dataset.

BERT-based Dense Passage Retrieval (DPR) question encoder for open-domain QA research, trained on multiple QA datasets

A French DPR model based on CamemBERT, optimized for French Q&A tasks, fine-tuned on PIAF, FQuAD, and SQuAD-FR datasets