jingtaozhan / RepBERT-Index
RepBERT is a competitive first-stage retrieval technique. It represents documents and queries with fixed-length contextualized embeddings. The inner products of them are regarded as relevance scores. Its efficiency is comparable to bag-of-words methods.
☆66Updated 3 years ago
Alternatives and similar repositories for RepBERT-Index:
Users that are interested in RepBERT-Index are comparing it to the libraries listed below
- SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.☆130Updated 3 years ago
- WSDM'2021, PROP and SIGIR'2021,B-PROP☆111Updated last year
- SIGIR 2021: Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling☆59Updated 3 years ago
- ☆17Updated 3 years ago
- Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation☆109Updated 3 years ago
- Source code of CIKM2021 Paper 'Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need'☆16Updated 3 years ago
- NAACL2021 - COIL Contextualized Lexical Retriever☆152Updated 3 years ago
- CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.☆52Updated 3 years ago
- WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval☆120Updated 7 months ago
- Source code for: On the Effect of Low-Frequency Terms on Neural-IR Models, SIGIR'19☆45Updated 5 years ago
- ☆23Updated last year
- Multi-stage passage ranking: monoBERT + duoBERT☆112Updated 4 years ago
- [SIGIR 2022] The official repo for the paper "Curriculum Learning for Dense Retrieval Distillation".☆23Updated 2 years ago
- Code and Data for SIGIR 2020 Paper "Few-Shot Generative Conversational Query Rewriting"☆65Updated last year
- code and data to faciliate BERT/ELECTRA for document ranking. Details refer to the paper - PARADE: Passage Representation Aggregation for…☆97Updated 2 years ago
- ☆82Updated last year
- ☆55Updated 3 years ago
- SIGIR'22 paper: Axiomatically Regularized Pre-training for Ad hoc Search☆24Updated last year
- EMNLP 2021 - Pre-training architectures for dense retrieval☆246Updated 3 years ago
- SIGIR'2022, Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction☆25Updated 2 years ago
- Code for the ECIR'22 paper "Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators"☆15Updated 3 years ago
- Tools for the TREC CAsT benchmark☆28Updated 2 years ago
- MIMICS: A Large-Scale Data Collection for Search Clarification☆76Updated 4 years ago
- ☆162Updated 4 years ago
- ☆12Updated 8 months ago
- Code for CEDR: Contextualized Embeddings for Document Ranking, accepted at SIGIR 2019.☆154Updated 4 years ago
- Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 20…☆109Updated 2 years ago
- ☆37Updated 2 years ago
- SIGIR 2022: GERE: Generative Evidence Retrieval for Fact Verification☆20Updated 2 years ago
- A toolkit for asynchronously validating dense retriever checkpoints during training.☆27Updated last year