CST's online demos

This page links to demo versions of our language technological tools, grammars and word bases.

Here you can see were you need language technological applications.

Tokeniser: CST's tokeniser creates segments containing one sentence each and divides these into tokens - words, numbers and punctuation.
Name recogniser: CST's named enity recogniser demarcates and classifies proper nouns in a text.
POS-tagger: The POS-tagger automatically assigns word class information to each word in a text, whether it is a noun, a verb, etc.
Lemmatiser: CST's lemmatiser reduces each word form in a text to the word's lemma form, the base form. The lemma form is the expression you would use to do a look up in a dictionary.
NP-recogniser: The Cass NP-chunker demarcates simple noun phrases.
Repetitiveness checker: The program finds repetitions of word groups that somehow stand out, using a statistical method. E.g. in a EU-related text: on the basis of or the high contracting parties.
Keywords: This program extracts 20 keywords characterising an input text.
Multi word terms: The program finds the most relevant adjective + noun combination among the words in the text.
Test a combination of tools: The aforementioned tools can work together in different constellations.
Summarisation tool: The summarisation tool (DanSum) can be used for automatic summarisation of Danish newspaper and text documents.
Computational Lexicon for Danish: User interface to STO.
Anonymisation: IDentification and ANonymisation of NAmes (IDANNA).

Emil Holms Kanal 2, building 22, 3, DK-2300 Copenhagen S

Web accessibility (in Danish)