Use this url to cite publication: https://cris.mruni.eu/cris/handle/007/16645
Options
Automatic Extraction of Lithuanian Cybersecurity Terms Using Deep Learning Approaches
Type of publication
Straipsnis konferencijos medžiagoje Web of Science duomenų bazėje / Article in conference proceedings in Web of Science database (P1a1)
Author(s)
Rokas, Aivaras | Vytauto Didžiojo universitetas |
Utka, Andrius | Vytauto Didžiojo universitetas |
Title
Automatic Extraction of Lithuanian Cybersecurity Terms Using Deep Learning Approaches
Date Issued
2020
Extent
p. 39-46
Is part of
Human Language Technologies – The Baltic Perspective Proceedings of the Ninth International Conference Baltic HLT 2020 / edited by Andrius Utka, Jurgita Vaičenonienė, Jolanta Kovalevskaitė, Danguolė Kalinauskaitė. Amsterdam; Berlin; Washington : IOS Press, 2020. ISBN 9781643681160.
Series/Report no.
Frontiers in artificial intelligence and applications, ISSN 0922-6389; vol. 328
Field of Science
Abstract
The paper presents the results of research on deep learning methods aiming to determine the most effective one for automatic extraction of Lithuanian terms from a specialized domain (cybersecurity) with very restricted resources. A semi-supervised approach to deep learning was chosen for the research as Lithuanian is a less resourced language and large amounts of data, necessary for unsupervised methods, are not available in the selected domain. The findings of the research show that Bi-LSTM network with Bidirectional Encoder Representations from Transformers (BERT) can achieve close to state-of-the-art results.
Type of document
type::text::conference output::conference proceedings::conference paper
ISBN (of the container)
9781643681160
9781643681177
ISSN (of the container)
0922-6389
1879-8314
WOS
000648590800006
SCOPUS
2-s2.0-85093357914
eLABa
69574076
Coverage Spatial
Nyderlandai / Netherlands (NL)
Language
Anglų / English (en)
Bibliographic Details
24
Project(s)
Research Council of Lithuania (LMTLT) |
Creative Commons License
Access Rights
Dalinė atviroji prieiga / Mixed Open Access
Journal | Cite Score | SNIP | SJR | Year | Quartile |
---|---|---|---|---|---|
Frontiers in Artificial Intelligence and Applications | 0.6 | 0.338 | 0.155 | 2020 | Q4 |