: Vocabulaire du TAL: KEA

NLP methods and tools > NLP software > KEA

KEA

An algorithm for extracting keyphrases from text documents. It can be either used for free indexing or for indexing with a controlled vocabulary. (Loterre)

In our experiments KEA was restricted to output no more than 15 keyphrases per document. (Chachra, Ben Abacha, Shooshan, Rodriguez & Demner-Fushman, 2016)
Medelyan and Witten extended the KEA to KEA++ which uses semantic information on terms and phrases extracted from a domain specific thesaurus thus enhances automatic keyphrase extraction (Medelyan and Witten 2006). (Zhang, Wang, Gong & Huang, 2016)
We should note that KEA is primarily designed for keyphrase extraction from scientific publications and whereas the position of the first occurrence might be indicative in research papers product reviews usually do not contain a summarizing "abstract" at the beginning. (Berend, Nagy, Móra & Vincze, 2011)

http://data.loterre.fr/ark:/67375/8LP-GVH06WD1-5

RDF/XML TURTLE JSON-LD Dernière modification le 03/05/2024

Loterre