A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

3 September 2024

Will Grathwohl

Papers citing "A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks"

2 / 2 papers shown

Title
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models Nandan Thakur Nils Reimers Andreas Rucklé Abhishek Srivastava Iryna Gurevych VLM 234 971 0 17 Apr 2021
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering Yingqi Qu Yuchen Ding Jing Liu Kai Liu Ruiyang Ren Xin Zhao Daxiang Dong Hua-Hong Wu Haifeng Wang RALM OffRL 214 594 0 16 Oct 2020