MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders Are Better Dense Retrievers

Kun Zhou; Xiao Liu; Yeyun Gong; Wayne Xin Zhao; Daxin Jiang; Nan Duan; Ji-Rong Wen

doi:10.1007/978-3-031-43415-0_37

ScienceGate Book Chapters

BOOK-CHAPTER

MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders Are Better Dense Retrievers

Kun Zhou Xiao Liu Yeyun Gong Wayne Xin Zhao Daxin Jiang Nan Duan Ji-Rong Wen

Year: 2023 Lecture notes in computer science Pages: 630-647 Publisher: Springer Science+Business Media

DOI: 10.1007/978-3-031-43415-0_37

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Autoencoder Initialization Encoder Artificial intelligence Bottleneck Task (project management) Transformer Code (set theory) Machine learning Artificial neural network

Metrics

Cited By

4.55

FWCI (Field Weighted Citation Impact)

Refs

0.94

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Domain Adaptation and Few-Shot Learning

Physical Sciences → Computer Science → Artificial Intelligence

MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders Are Better Dense Retrievers

Metrics

Citation History

Topics

Related Documents

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Non-salient Object Segmentation in Medical Images via Pre-trained Multi-granularity Masked Autoencoders

Enhancing Emotion Recognition with Pre-trained Masked Autoencoders and Sequential Learning

Improving News Recommendation via Bottlenecked Multi-task Pre-training

Multimae Meets Earth Observation: Pre-Training Multi-Modal Multi-Task Masked Autoencoders for Earth Observation Tasks