Automatic extraction of keywords from scientific publications for indexing and open data in agronomy

摘要

With the large amounts of textual data related to agriculture now available, indexing becomes a crucial issue for research organizations. One way to index documents consists in extracting terminology. This paper investigates the use and combination of text mining methodologies to highlight and publish the most appropriate terms from documents in open data systems. Experiments conducted on CIRAD data, show the validity of the approach used to extract new and relevant terms.