Dutch Language Institute

The Dutch Language Institute (INT) is a research institute with the mission to ensure a high-quality digital infrastructure for the Dutch language. Through the compilation of corpora, lexical databases and references works, and by developing language tools and other software applications, we support research and development in linguistics, the digital humanities, language education and language-centered AI.

Find out more about our main research topics by clicking on the tiles below, or visit our about page for further information about the institute.

FAIR access to language resources

As CLARIN-B centre and resource deposit/repository, we contribute to best practices for FAIR (Findable, Accessible, Interoperable, Reusable) and sustainable availability of language data and tools for Dutch and across the EU.

Corpus compilation and publishing

Our research focuses on data models, data processing and data publishing techniques for creating corpora of historical, modern, written and spoken Dutch, its dialects, and Dutch and Flemish Sign Language

Lexicography, dialectology, terminology and grammar

The INT develops data models, methods and workflows for documenting the lexicon and grammar of Dutch in all its variety, through the ages.

Software development

Our R&D focuses on corpus software, linguistic databases, tooling for linguistic annotation and validation, and applications for special language needs.

Computational Linguistics and AI

The INT carries out applied research into NLP and Artificial Intelligence for Dutch and for Dutch and Flemish Sign Language.

Digitisation of historical texts

As founding member of IMPACT Digitisation centre of competence, we offer expertise in digitisation, OCR and further processing of historical documents

European R&D networks

In addition to CLARIN, the INT has been, and is, an active member in different European networks for building language resources and infrastructures. You’ll find a selection below (click here for an overview).

European Language Data Space

ENEOLI (neologisms and lexical innovation )

UniDive (language diversity and technology)

Elexis Association (lexicography)

Collaborations

Within the Dutch speaking regions, the INT collaborates closely with many organizations, foremost the Taalunie (Union for the Dutch Language), to promote research, teaching and use of the Dutch language. Internationally, the INT cooperates with similar organisations for other languages within EFNIL, and with other research institutes in numerous projects. INT also host internships and research visits. Find out more on our collaborate page on how to cooperate with us.