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
Related projects ⓘ
Alternatives and complementary repositories for RepBERT-Index
- SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.☆126Updated 2 years ago
- SIGIR 2021: Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling☆58Updated 3 years ago
- ☆17Updated 3 years ago
- WSDM'2021, PROP and SIGIR'2021,B-PROP☆110Updated last year
- NAACL2021 - COIL Contextualized Lexical Retriever☆149Updated 3 years ago
- SIGIR'2022, Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction☆24Updated 2 years ago
- ☆23Updated last year
- Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation☆108Updated 3 years ago
- CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.☆50Updated 2 years ago
- WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval☆118Updated 3 months ago
- Multi-stage passage ranking: monoBERT + duoBERT☆112Updated 3 years ago
- Source code of CIKM2021 Paper 'Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need'☆17Updated 3 years ago
- Tools for the TREC CAsT benchmark☆26Updated last year
- 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 last year
- EMNLP 2021 - Pre-training architectures for dense retrieval☆243Updated 2 years ago
- ☆78Updated last year
- ☆54Updated 3 years ago
- Code for CEDR: Contextualized Embeddings for Document Ranking, accepted at SIGIR 2019.☆155Updated 4 years ago
- Source code for: On the Effect of Low-Frequency Terms on Neural-IR Models, SIGIR'19☆45Updated 5 years ago
- ☆161Updated 4 years ago
- ☆37Updated 2 years ago
- [SIGIR 2022] The official repo for the paper "Curriculum Learning for Dense Retrieval Distillation".☆23Updated 2 years ago
- ☆33Updated last year
- Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 20…☆106Updated 2 years ago
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆143Updated 2 years ago
- ☆17Updated last year
- An easy-to-use tool for phrase encoding and topic mining (unsupervised aspect extraction); Code base for ACL 2022 paper, UCTopic: Unsuper…☆43Updated last year
- Unified Learned Sparse Retrieval Framework☆60Updated 6 months ago
- SIGIR'22 paper: Axiomatically Regularized Pre-training for Ad hoc Search☆24Updated last year