K-Dutch

Mediawiki:Mainpage

Welkom op K-Dutch, de plek voor iedereen die iets over het Nederlands wil weten: taalkundige eigenschappen, taaladvies, beschikbare tools en data, etymologie, dialect, ....

K-Dutch is een CLARIN Kenniscentrum. Het wordt gehost door het Instituut voor de Nederlandse Taal, dat ook een gecertificeerd CLARIN-B centrum is en dat verschillende resources voor het Nederlands host. Over 't algemeen zijn deze gratis en vrij beschikbaar voor onderzoeksdoeleinden. K-Dutch is een initiatief van CLARIN-ERIC en CLARIN-BE.

De status van het Nederlands met betrekking tot taaltechnologie wordt beschreven in

• Korte versie (Engels): Steurs, Vandeghinste and Daelemans (2023). Language Report Dutch. In : Rehm, G., Way, A. (eds) European Language Equality. Cognitive Technologies. Springer, Cham. https://doi.org/10.1007/978-3-031-28819-7_12
• Langere versie (Engels): Steurs, Vandeghinste and Daelemans (2022). Report on Dutch. Project deliverable. European Language Equality.

Uw bijdrage aan deze pagina's is welkom. Gelieve de INT servicedesk te contacteren servicedesk@ivdnt.org met als onderwerp K-Dutch

Taalkundige onderwerpen

Grammatica

• Fonologie, Morfologie en Syntaxis: Taalportaal
• Morfosyntaxis
• Syntactische Atlas van de Nederlandse Dialecten (SAND)
• Nederlandse beschrijvende grammatica: e-ANS
• Grambank

Lexicografie

• Nederlandse woordenboeken
• Het ELEXIS Project
• White paper: The Future of Academic Lexicography

Terminology

• The Centre of Expertise for Dutch Terminology
• Academic Language
• Medical Terminology
• Dutch as a scientific language
• Legal Terminology

Spelling

• Woordenlijst.org (Official Dutch Word List)
• Spelling Certification Mark

Linguistic resources: datasets

Corpora

Lexical Resources

N-grams

• Character N-grams

Tools for Dutch

Normalisation

• Format conversion
• Spell checking
• TiCCLops: Text-Induced Corpus Clean-up online processing system: no longer available
• Normalisation Demo

Language Learning

• Schrijfassistent
• Schrijfassistent at De Standaard
• NedBox: Online exercises to learn Dutch
• Oefenen.nl: Online exercises to learn Dutch
• Woordcombinaties: Verbs and their combination patterns
• Orient+: A serious game to enhance academic vocabulary
• Taalwinkel: Language Advice

Automatic linguistic annotation

• Basic language processing
• Deep parsing

Speech processing

• Spoken Language Recognition
• Speech recognition
• Speech synthesis

Natural Language Processing

• Language Modeling
• Machine translation
• Coreference resolution
• Compound splitting
• Word Sense Disambiguation
• Text classification
• Sentiment analysis
• Readability
• Clinical NLP

Resource querying

• Corpus querying
• Treebank querying

Machine translation

Translation Engines

Publicly available machine translation engines from or to Dutch:

• DeepL
• Google translate
• Bing Microsoft translator
• Reverso
• eTranslation from the European Union
• MATEO No Language Left Behind

MT Evaluation

• MATEO Machine Translation Evaluation Online

Terminology extraction

• Termtreffer. Ask for login at terminologie@ivdnt.org.
• D-Terminer demo. Terminology extraction for Dutch, English, French and German. (Rigouts Terryn, A. (2021). D-TERMINE: Data-driven Term Extraction Methodologies Investigated [Doctoral thesis]. Ghent University.)

Terminology management

• IATE (Interactive Terminology for Europe) is the EU's terminology management system. It’s the shared terminology management system of the institutions of the European Union and it contains more than 7 million terms in 26 languages covering more than 100 domains of the EU legislation.

Other

• Previously unmentioned CLARIN projects at INT
• Language and Speech Tools at Radboud Nijmegen. e.g. T-scan, an analysis tool for dutch texts to assess the complexity of the text.
• OpeNER is a language analysis toolchain helping (academic) researchers and companies make sense out of natural language analysis”. It consist of easy to install, improve and configure components to e.g. detect the language of a text, determine polarisation of texts (sentiment analysis), detect what topics are included in the text,... The supported language set currently consists of: English, Spanish, Italian, German and Dutch.
• GATE (General Architecture for Text Engineering) is a Java suite of tools originally developed at the University of Sheffield and it is used for many natural language processing tasks, including information extraction. (Dutch services in GATE Cloud).
• Speech Repository is an online e-learning tool. It contains video recordings of real-life speeches and tailor-made pedagogical material speeches which give the interpreter and interpreting students an opportunity to practise and improve their interpretation skills.
• Subtitle Workshop is a free application for creating, editing, and converting text-based subtitle files.
• YouDescribe is a free, web-based platform for adding audio description to YouTube content.
• Audacity is an audio recording and editing software application that is open source.

Helpdesk

For information about Dutch: If you cannot find the answers to your questions on this wiki, you can send your question to servicedesk@ivdnt.org . Your questions will be forwarded as soon as possible to the appropriate experts and you should receive an answer within two working days.

You can also ask us for information and assistance with the use of data and tools.

Other Services

• Best practice documents and guidelines
• Internships
• Consulting
• CLARIN for Dutch

Vragen en Antwoorden

Op de Vragen en Antwoordenpagina houden we de vragen bij die we ontvingen. Dit groeit uit tot een repository van K-Dutch antwoorden op uw vragen.