Online CST tools

CST has developed a wide range of language technology tools and resources that we make available. The tools mentioned below are mainly intended for teaching and demonstration use.

If you need to process larger volumes of documents, you should use one of these toolboxes:

CLARIN-DK

If you need a fast, basic processing of Danish or English texts, you can go to the tools in clarin.dk. Here you can upload one or more files, select one of the predefined processes and download the result.

Text Tonsorium

If you want a more tailored solution, you should go to our Text Tonsorium, which can be briefly described as an experimental linguistic sandbox. Here is a wealth of tools for different languages. Text Tonsorium does not require that you to know much about the individual tools, because once you have specified the output you want, the tools are automatically put together in a workflow so they can produce the specified output.

Combine tools

You can combine the online tools or
you access each tool from the list below.

Keyword extractor

Extracts 20 keywords characterising an input text.

Lemmatiser

Reduces all words in a text to their base form, the lemma.

Multi word terms

Lists all occurrences of the same multi word term from a text.

Name recogniser

Classifies names as proper names, locations or other names.

NP recogniser

Collects words that constitute noun phrases
(NPs).

POS tagger

Marks each word in a text with information
about word class and morphological features.

Tokeniser

Tokenisation and segmentation program for
text and RTF files.

Other online NLP tools

Third-party NLP software