microsoft / ANCE
A novel embedding training algorithm leveraging ANN search and achieved SOTA retrieval on Trec DL 2019 and OpenQA benchmarks
☆368Updated last year
Alternatives and similar repositories for ANCE:
Users that are interested in ANCE are comparing it to the libraries listed below
- EMNLP 2021 - Pre-training architectures for dense retrieval☆247Updated 3 years ago
- A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Re…☆322Updated last year
- Build Text Rerankers with Deep Language Models☆261Updated last year
- An Open-Source Package for Information Retrieval.☆448Updated 2 years ago
- docTTTTTquery document expansion model☆362Updated 2 years ago
- Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch☆262Updated 2 years ago
- ☆162Updated 4 years ago
- ☆480Updated 3 years ago
- DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.☆319Updated 3 years ago
- SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.☆131Updated 3 years ago
- NAACL2021 - COIL Contextualized Lexical Retriever☆152Updated 3 years ago
- A library to conduct ranking experiments with transformers.☆161Updated last year
- Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations☆132Updated 10 months ago
- a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini☆350Updated last year
- WSDM'2021, PROP and SIGIR'2021,B-PROP☆111Updated last year
- [ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.o…☆603Updated 2 years ago
- Code associated with the Don't Stop Pretraining ACL 2020 paper☆529Updated 3 years ago
- Codebase for RetroMAE and beyond.☆255Updated 9 months ago
- ☆211Updated 2 years ago
- RepBERT is a competitive first-stage retrieval technique. It represents documents and queries with fixed-length contextualized embeddings…☆66Updated 3 years ago
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆145Updated 3 years ago
- Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"☆202Updated 3 years ago
- MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, …☆316Updated last year
- ☆166Updated last year
- Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation☆109Updated 3 years ago
- This project provides an unsupervised framework for mining and tagging quality phrases on text corpora with pretrained language models (K…☆172Updated 2 years ago
- WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval☆120Updated 7 months ago
- Code for CEDR: Contextualized Embeddings for Document Ranking, accepted at SIGIR 2019.☆155Updated 4 years ago
- pytrec_eval is an Information Retrieval evaluation tool for Python, based on the popular trec_eval.☆302Updated last year
- Fusion-in-Decoder☆564Updated last year