paper-with-me

홈 › Papers

LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval

2022-03-11 · Findings (ACL) 2022 5 · Canwen Xu, Daya Guo, Nan Duan, Julian McAuley

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.

📄 PDF Abstract BibTeX arXiv:2203.06169

Code (1)

jetrunner/laprador 공식 구현 pytorch

Tasks

Contrastive LearningRe-RankingRetrievalText RetrievalZero-shot Text Retrieval

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Leveraging LLMs for Unsupervised Dense Retriever Ranking

2024-02-07 · Ekaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh, Guido Zuccon

In this paper we present Large Language Model Assisted Retrieval Model Ranking (LARMOR), an effective unsupervised approach that leverages LLMs for selecting which dense retriever to use on a test corpus (target). Dense …

Language ModellingLarge Language Model

Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval

2023-11-27 · Fan Jiang, Qiongkai Xu, Tom Drummond, Trevor Cohn

Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are unwieldy, such as requiring explicit super…

Passage RetrievalRetrieval

Precise Zero-Shot Dense Retrieval without Relevance Labels

2022-12-20 · Luyu Gao, Xueguang Ma, Jimmy Lin, Jamie Callan

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this pape…

Fact VerificationInstruction FollowingLanguage ModelingLanguage Modelling+2

Selecting which Dense Retriever to use for Zero-Shot Search

2023-09-18 · Ekaterina Khramtsova, Shengyao Zhuang, Mahsa Baktashmotlagh, Xi Wang 외

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily availab…

Information RetrievalRetrieval

Can a Frozen Pretrained Language Model be used for Zero-shot Neural Retrieval on Entity-centric Questions?

2023-03-09 · Yasuto Hoshi, Daisuke Miyashita, Yasuhiro Morioka, Youyang Ng 외

Neural document retrievers, including dense passage retrieval (DPR), have outperformed classical lexical-matching retrievers, such as BM25, when fine-tuned and tested on specific question-answering datasets. However, it …

Domain GeneralizationLanguage ModelingLanguage ModellingPassage Retrieval+2