jingtaozhan / JPQView external linksLinks
CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.
☆52Feb 19, 2022Updated 3 years ago
Alternatives and similar repositories for JPQ
Users that are interested in JPQ are comparing it to the libraries listed below
Sorting:
- WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval☆120Aug 7, 2024Updated last year
- SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.☆128Feb 15, 2022Updated 4 years ago
- Source code of CIKM2021 Paper 'Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need'☆16Aug 30, 2021Updated 4 years ago
- An easy-to-use python toolkit for flexibly adapting various neural ranking models to target domain.☆60May 17, 2023Updated 2 years ago
- A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks☆383Jan 6, 2026Updated last month
- CIKM 2022: Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models☆11Aug 4, 2022Updated 3 years ago
- RepBERT is a competitive first-stage retrieval technique. It represents documents and queries with fixed-length contextualized embeddings…☆66Oct 13, 2021Updated 4 years ago
- Source code of paper 'LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval' (WWW 2023)☆22Aug 28, 2023Updated 2 years ago
- [SIGIR 2022] The official repo for the paper "Curriculum Learning for Dense Retrieval Distillation".☆23Apr 29, 2022Updated 3 years ago
- Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering☆175Jun 6, 2021Updated 4 years ago
- Code for paper "Conversational Product Search Based on Negative Feedback"☆12Jun 26, 2020Updated 5 years ago
- ☆13Nov 9, 2021Updated 4 years ago
- NAACL2021 - COIL Contextualized Lexical Retriever☆157Jul 27, 2021Updated 4 years ago
- Dense hybrid representations for text retrieval☆64Apr 3, 2023Updated 2 years ago
- Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch