Dvikalbis automatinis terminų atpažinimas

Abstract

The aim of the project is to design a methodology for automatic extraction of English and Lithuanian terms in a special domain from parallel and comparable corpora and create a bilingual termbase, which will be based on the empirical data and will be publicly available on the Internet. Cybersecurity (CS) terminology is chosen as a special domain for the project. The scientific problem to be solved is the automatic extraction of terminographic data from bilingual resources, i.e. parallel and comparable corpora, when one of the languages is under-resourced and morphologically rich. An innovative methodology will be created in the course of the project implementation, which, to our knowledge, has not been applied in Lithuania yet. It will provide the possibility to extract terms not only from original texts and their translations, but also from comparable original texts of the same domain in several languages. Thus, the collected data will reflect the usage of the terms both in international and national documents. The implementers of the project will aim to cope with the challenges such as limited bilingual English-Lithuanian resources and the lack of such research for morphologically rich languages. The results of the research and developed methodology will be presented in scientific papers and conferences. In addition to the bilingual termbase, the implementers of the project will produce valuable empirical data - English-Lithuanian parallel and comparable corpora - and make them available to the public (in CLARIN repository). The CS area was chosen because of its special relevance in today's information society. This area is particularly dynamic, as new documents of the CS area are constantly drawn up, new concepts are developed, but their names have not been fixed in the Lithuanian language yet. Thus, the new CS concepts are often expressed by several terms or even by the name used in the original language. Therefore, the CS termbase is now particularly relevant to drafters of legal and administrative acts, translators, IT professionals and the general public. The CS termbase could be used as a model for development of termbases in other domains as well. Due to ever-changing realia, large volumes of texts, automatic methods have become an indispensable tool for collecting, systematising, defining, and constantly updating terminology resources. Therefore, the methodology developed during the project will be useful for the management of Lithuanian terminology of various domains.