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.
The paper describes in detail a unique study programme of English for Specific Purposes and the Second Foreign Language created by the teaching staff of the Institute of Humanities, Mykolas Romeris University in Vilnius, Lithuania, to meet the expectations and requirements of the current/future labour market. The need for the programme arose from the requests of both possible applicants and employers. Since its launch in 2012 the programme gathered impetus and received considerable interest from abroad as well: there have been growing numbers of students from China, Japan, Norway, Israel, Ukraine, Belarus, Poland, etc. enrolling into the study programme. Additionally, this BA study programme was tailored to meet the needs of students from other faculties and opened as a minor studies programme for students majoring in law, business and public administration, communication. Within several years of the successful implementation a greater choice of second languages has been offered, namely, Korean, Norwegian, German, Spanish and French. The employment rate and feedback from the alumni of the programme and their employers testify the success of the BA programme in the area of ESP in terms of providing graduates with the indispensable multilingual, cultural and communicative competencies. This enables to maintain and develop the programme further on.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.