Publication details

Evaluation of the Sketch Engine Thesaurus on Analogy Queries

Investor logo


Year of publication 2016
Type Article in Proceedings
Conference Tenth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2016
MU Faculty or unit

Faculty of Informatics

Field Informatics
Keywords distributional thesaurus; analogy queries
Description Recent research on vector representation of words in texts bring new methods of evaluating distributional thesauri. One of such methods is the task of analogy queries. We evaluated the Sketch Engine thesaurus on a subset of analogy queries using several similarity options. We show that Jaccard similarity is better than the cosine one for bigger corpora, it even substantially outperforms the word2vec system.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info