@inproceedings{xu2022laprador,
author = {Xu, Canwen and Guo, Daya and Duan, Nan and McAuley, Julian},
title = {LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval},
booktitle = {ACL 2022},
year = {2022},
month = {May},
abstract = {In this paper, we propose LaPraDoR, a pretrained dual-tower dense retriever that does not require any supervised data for training. Specifically, we first present Iterative Contrastive Learning (ICoL) that iteratively trains the query and document encoders with a cache mechanism. ICoL not only enlarges the number of negative instances but also keeps representations of cached examples in the same hidden space. We then propose Lexicon-Enhanced Dense Retrieval (LEDR) as a simple yet effective way to enhance dense retrieval with lexical matching. We evaluate LaPraDoR on the recently proposed BEIR benchmark, including 18 datasets of 9 zero-shot text retrieval tasks. Experimental results show that LaPraDoR achieves state-of-the-art performance compared with supervised dense retrieval models, and further analysis reveals the effectiveness of our training strategy and objectives. Compared to re-ranking, our lexicon-enhanced approach can be run in milliseconds (22.5x faster) while achieving superior performance.},
url = {http://approjects.co.za/?big=en-us/research/publication/laprador-unsupervised-pretrained-dense-retriever-for-zero-shot-text-retrieval/},
}