From the webpage:
Used for indexing information resources, Agrotagger is a keyword extractor that uses the AGROVOC thesaurus as its set of allowable keywords. It can extract from Microsoft Office documents, PDF files and web pages.
…
There are currently several available services that can be accessed either as web interfaces for manual document upload or as REST web services that can be programmatically invoked:
Following up on the AGROVOC thesaurus, FAO thesaurus links with reegle, and found this interesting resource.
Doesn’t seem like a big jump to have a set of keyword that create topics, associations and occurrences With document author(s), journal, place of employment, etc.
Would need proofing but on the other hand could produce a topic map for proofing tout de suite. (No Michel, I had to look it up. 😉 )