The Sketch Engine

Abstract

The Sketch Engine is a leading corpus tool, widely used in lexicography. Now, at 10 years old, it is mature software. The Sketch Engine website offers many ready-to-use corpora, and tools for users to build, upload and install their own corpora. The paper describes the core functions (word sketches, concordancing, thesaurus). It outlines the different kinds of users, and the approach taken to working with many different languages. It then reviews the kinds of corpora available in the Sketch Engine, gives a brief tour of some of the innovations from the last few years, and surveys other corpus tools and websites.

Man’s Gender and Age as Based on the Collocations of the Estonian Word Mees ‘Man’

“…Research data was retrieved by means of the Sketch Engine (see Kilgarriff et al 2004), which enables collocations to be found using lexico-grammatical constructions. The program recognises collocations on the basis of the output of automatic morphological analysis (part of speech plus grammatical features) combined with statistical methods.…”

“…The corpus based study uses the Estonian Reference Corpus (203 million words altogether) where 75% of the texts are journalistic, so the results will mainly show how people are depicted in the media. Research data was retrieved by means of the Sketch Engine (see Kilgarriff et al 2004), which enables collocations to be found using lexico-grammatical constructions. Two lexico-grammatical constructions were analysed: the adjectival modifiers of nouns and verbs co-occurring with a noun functioning as a subject.…”

Comparative evaluation of tools for Arabic corpora search and analysis

“…WordSmith Tools 6.0 (Scott, 2008(Scott, , 2012 5. The Sketch Engine (Kilgarriff et al, 2004;Kilgarrif 2014) 6. IntelliText Corpus Queries (Wilson et al,.…”

“…The Sketch Engine (Kilgarriff et al, 2004(Kilgarriff et al, , 2014) is a commercial webbased tool for corpus analysis developed by Lexical Computing Ltd. In addition to the corpora searching tool, the users are provided with corpora in many languages including Arabic.…”

“…A number of these search and analysis tools are web-based, e.g. The Sketch Engine (Kilgarriff et al, 2004;Kilgarriff, 2014), IntelliText Corpus Queries (Wilson et al,. 2010;Sharoff, 2014), CQPweb at Lancaster (Hardie, 2012(Hardie, , 2014, so in order to use them, researchers need to be persistently online.…”