Inspired from: Duncan Hull GROBID-Dictionaries ? Automatic extraction of TEI structures from digitised dictionaries (Khemakhem et al. 2017) ? Input: PDF (soon ALTO) ? Output: TEI compliant lexical resource ? Spin-off from GROBID, 2015. ,
Automatic extraction of structural data from scholarly papers ? Metadata (author, title, affiliations, keywords, abstract), bibliography, ? full text ? And open source? ? Uses Conditional Random Fields (CRF, 2010. ,
, , 2009.
SIL) a lexical time-space machine => bringing back knowledge to the lexicographic folk, Basnage: a drop in the legacy ocean ,