Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations
To improve the R&D process by reducing duplicated bug tickets, we used the idea of composing a BERT encoder as a Siamese network to create a system for finding similar existing tickets. We proposed several different methods of generating artificial ticket pairs to augment the training set. Two p...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/22/3664 |
_version_ | 1797465519743303680 |
---|---|
author | Sebastian Zarębski Aleksander Kuzmich Sebastian Sitko Krzysztof Rusek Piotr Chołda |
author_facet | Sebastian Zarębski Aleksander Kuzmich Sebastian Sitko Krzysztof Rusek Piotr Chołda |
author_sort | Sebastian Zarębski |
collection | DOAJ |
description | To improve the R&D process by reducing duplicated bug tickets, we used the idea of composing a BERT encoder as a Siamese network to create a system for finding similar existing tickets. We proposed several different methods of generating artificial ticket pairs to augment the training set. Two phases of training were conducted. The first showed that only approximately 9% of pairs were correctly identified as certainly similar. Only 48% of the test samples were found to be pairs of similar tickets. With fine-tuning, we improved that result to 81%, which is a number describing a set of common decisions between the engineer in the company and the solution presented. With this tool, engineers in the company receive a specialized instrument with the ability to evaluate tickets related to a security bug at a level close to an experienced company employee. Therefore, we propose a new engineering application in corporate practice in a very important area with Siamese network methods that are widely known and recognized for their efficiency. |
first_indexed | 2024-03-09T18:23:36Z |
format | Article |
id | doaj.art-901f9acddbbd4928a8515cab660d35ba |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T18:23:36Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-901f9acddbbd4928a8515cab660d35ba2023-11-24T08:08:29ZengMDPI AGElectronics2079-92922022-11-011122366410.3390/electronics11223664Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base StationsSebastian Zarębski0Aleksander Kuzmich1Sebastian Sitko2Krzysztof Rusek3Piotr Chołda4NOKIA, Bobrzyńskiego 46, 30-348 Kraków, PolandNOKIA, Bobrzyńskiego 46, 30-348 Kraków, PolandNOKIA, Bobrzyńskiego 46, 30-348 Kraków, PolandInstitute of Telecommunications, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, PolandInstitute of Telecommunications, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, PolandTo improve the R&D process by reducing duplicated bug tickets, we used the idea of composing a BERT encoder as a Siamese network to create a system for finding similar existing tickets. We proposed several different methods of generating artificial ticket pairs to augment the training set. Two phases of training were conducted. The first showed that only approximately 9% of pairs were correctly identified as certainly similar. Only 48% of the test samples were found to be pairs of similar tickets. With fine-tuning, we improved that result to 81%, which is a number describing a set of common decisions between the engineer in the company and the solution presented. With this tool, engineers in the company receive a specialized instrument with the ability to evaluate tickets related to a security bug at a level close to an experienced company employee. Therefore, we propose a new engineering application in corporate practice in a very important area with Siamese network methods that are widely known and recognized for their efficiency.https://www.mdpi.com/2079-9292/11/22/3664fault detectionmachine learningnatural language processing |
spellingShingle | Sebastian Zarębski Aleksander Kuzmich Sebastian Sitko Krzysztof Rusek Piotr Chołda Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations Electronics fault detection machine learning natural language processing |
title | Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations |
title_full | Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations |
title_fullStr | Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations |
title_full_unstemmed | Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations |
title_short | Siamese Neural Networks on the Trail of Similarity in Bugs in 5G Mobile Network Base Stations |
title_sort | siamese neural networks on the trail of similarity in bugs in 5g mobile network base stations |
topic | fault detection machine learning natural language processing |
url | https://www.mdpi.com/2079-9292/11/22/3664 |
work_keys_str_mv | AT sebastianzarebski siameseneuralnetworksonthetrailofsimilarityinbugsin5gmobilenetworkbasestations AT aleksanderkuzmich siameseneuralnetworksonthetrailofsimilarityinbugsin5gmobilenetworkbasestations AT sebastiansitko siameseneuralnetworksonthetrailofsimilarityinbugsin5gmobilenetworkbasestations AT krzysztofrusek siameseneuralnetworksonthetrailofsimilarityinbugsin5gmobilenetworkbasestations AT piotrchołda siameseneuralnetworksonthetrailofsimilarityinbugsin5gmobilenetworkbasestations |