API

for Natural Language Processing (NLP), corpus building and corpus searching

The Sketch Engine API was developed to enable other software to exploit the NLP functionality of Sketch Engine. The Sketch Engine API supports nearly 100 % of the complete corpus building and corpus search features provided by Sketch Engine.

We offer a complete functionality for at least 20 major languages but certain features might not be available for all 90+ languages. Please contact us to check the extent of support for your language.

One-off jobs

If you need a large amount of langauge data processed or generated only once, it is usually more practical and cost-effective to have it done as a one-off job. An example can be a generation of a word database of all words in a language or processing a multi-billion-word data set into a text corpus. The language data will be processed by the Lexical Computing team and delivered in a format according to your specification.

Examples of API use

retrieval of

  • Good Dictionary EXamples
  • collocations
  • synonyms

processing of text to obtain

  • part-of-speech tagging
  • terms and keywords

Supported languages

Please check the langauges and the size of corpora we already have for each language.

The language processing API is available for these languages

Not all features are available with all languages, please contact us for details.

a course in lexicography and lexical computing