Seedlabs
companyCorpus Linguistics / Language TechnologyUnited Kingdom

SketchEngine (Lexical Computing)

Corpus management and query platform for linguists, lexicographers, and language researchers worldwide.

Sketch Engine – Official Website

Lexical Computing is a research company founded by Adam Kilgarriff in 2003, working at the intersection of corpus and computational linguistics. Its flagship product, Sketch Engine, is a leading corpus management and query tool used by linguists, lexicographers, translators, and publishers globally, grounded in an empiricist approach to language study where corpora play a central role.

Sketch Engine provides access to 1 trillion words across 800 ready-to-use corpora in 100+ languages, with individual corpora reaching up to 87 billion words. Its signature feature, the Word Sketch, automatically summarises a word's grammatical and collocational behaviour — first introduced in the Macmillan English Dictionary in 2002. Users can query billions of words in seconds, explore concordances and word lists, and build their own corpora by uploading texts or crawling the web.

The platform is a first-choice solution for major publishers, universities, translation agencies, and national language institutes. Customers include Oxford University Press, Dictionnaires Le Robert, Macmillan, and Shogakukan, with four of the UK's five largest dictionary publishers among its users. National language institutes in nine European countries and over 200 universities worldwide rely on it for research, dictionary production, and language teaching.

Lexical Computing employs staff in the UK and the Czech Republic. Adam Kilgarriff led the company from its founding until his death in 2015; Vojtěch Kovář serves as CTO, leading the technical team. Innovations in corpus linguistics, NLP, and large-scale text analysis are directly relevant to the company's core product and mission.

Ideas that could help SketchEngine (Lexical Computing)