Automatic Extraction of Lithuanian Cybersecurity Terms Using Deep Learning Approaches

• Aivaras Rokas ^[1] ; Sigita Rackevičienė ^[2] ; Andrius Utka ^[1]
  1. [1] Vytautas Magnus University

     Vytautas Magnus University

     Lituania

     
  2. [2] Mykolas Romeris University, Lithuania
• Localización: Human Language Technologies – The Baltic Perspective: Proceedings of the Ninth International Conference Baltic HLT 2020 / coord. por Andrius Utka, Jurgita Vaičenonienė, Jolanta Kovalevskaitė, Danguolė Kalinauskaitė, 2024, ISBN 978-1-64368-116-0, págs. 39-46
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • The paper presents the results of research on deep learning methodsaiming to determine the most effective one for automatic extraction of Lithuanianterms from a specialized domain (cybersecurity) with very restricted resources. Asemi-supervised approach to deep learning was chosen for the research asLithuanian is a less resourced language and large amounts of data, necessary forunsupervised methods, are not available in the selected domain. The findings of theresearch show that Bi-LSTM network with Bidirectional Encoder Representationsfrom Transformers (BERT) can achieve close to state-of-the-art results