Aivaras Rokas, Sigita Rackevičienė, Andrius Utka
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
© 2001-2024 Fundación Dialnet · Todos los derechos reservados