At present in any entity or company it is essential to have linguistic resources that contemplate multilingualism. In a context in which multilingualism is imposed, it is increasingly important to create linguistic resources based on language technologies – regardless of the language – that allow the information to be treated in a unified and effective manner and subsequently used appropriately.
To do this, we work in various areas, such as the automatic extraction of terminology and entities, technologies for the management of extracted terminology and tools to create and complete corpus. Finally, we also developed tools to help write in Basque.
Our main lines of research are:
- Automatic extraction: extractors of entities and terms, both monolingual and multilingual
- Automatic lexicography
- Automatic corpus creation
- Smart Correctors