Please use this identifier to cite or link to this item:
Publication type: Conference paper
Type of review: Peer review (publication)
Title: Detecting errors in databases with bidirectional recurrent neural networks
Authors: Holzer, Severin
Stockinger, Kurt
et. al: No
DOI: 10.21256/zhaw-24615
Proceedings: Proceedings of EDBT 2022
Conference details: 25th International Conference on Extending Database Technology, Edinburgh (online), 29 March - 1 April 2022
Issue Date: Mar-2022
Publisher / Ed. Institution: OpenProceedings
ISBN: 978-3-89318-086-8
Language: English
Subjects: Error detection; Database; Neural network
Subject (DDC): 006: Special computer methods
Abstract: In this paper we introduce an architecture based on bidirectional recurrent neural networks to detect errors in databases. The experimental results with 6 different datasets demonstrate that our approach outperforms state-of-the-art error detection systems when considering the average of the F1-scores over all datasets. Moreover, our approach achieves a lower standard deviation than existing work, which shows that our system is more robust. Finally, our approach does not require additional data augmentation techniques to achieve high F1-scores.
Fulltext version: Published version
License (according to publishing contract): CC BY-NC-ND 4.0: Attribution - Non commercial - No derivatives 4.0 International
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Holzer-Stockinger_Error-Dectection_EDBT.pdf321.86 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.