Dense retrievers, retriever pre-training, synthetic query generation, domain adaptation, sentence embeddings, re-ranking, and query rewriting. Sorted by the paper's first public release (oldest first).
[2019.06] Latent Retrieval for Weakly Supervised Open Domain Question Answering (ORQA)
[2020.04] Dense Passage Retrieval for Open-Domain Question Answering (DPR)
[2020.07] Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval (ANCE)
[2021.01] Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup (GradCache)
[2021.04] Condenser: a Pre-training Architecture for Dense Retrieval
[2021.05] Few-Shot Conversational Dense Retrieval (ConvDR)
[2021.08] Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
[2021.12] GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
[2021.12] Large Dual Encoders Are Generalizable Retrievers (GTR)
[2021.12] Unsupervised Dense Information Retrieval with Contrastive Learning (Contriever)
[2022.01] Unified Question Generation with Continual Lifelong Learning
[2022.01] Text and Code Embeddings by Contrastive Pre-Training (cpt)
[2022.02] InPars: Data Augmentation for Information Retrieval using Large Language Models
[2022.03] LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval
[2022.04] Improving Passage Retrieval with Zero-Shot Question Generation (UPR)
[2022.06] No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval