🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.
- Updated
Dec 19, 2023 - Python
🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.
Train Models Contrastively in Pytorch
Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
EMNLP 2021 - Pre-training architectures for dense retrieval
A Python Search Engine for Humans 🥸
[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
Train Dense Passage Retriever (DPR) with a single GPU
WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval
Nature Biotechnology: Ultra-fast, sensitive detection of protein remote homologs using deep dense retrieval
SimXNS is a research project for information retrieval. This repo contains official implementations by MSRA NLC team.
Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"
An easy-to-use python toolkit for flexibly adapting various neural ranking models to target domain.
Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
[EMNLP 2022] This is the code repo for our EMNLP‘22 paper "COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning".
Code for the ACL 2023 long paper - Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering
A Flexible Toolkit for Dense Retrieval
Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.
We introduce the direct document relevance optimization (DDRO) for training a pairwise ranker model. DDRO encourages the model to focus on document-level relevance during generation
Add a description, image, and links to the dense-retrieval topic page so that developers can more easily learn about it.
To associate your repository with the dense-retrieval topic, visit your repo's landing page and select "manage topics."