Publication Date:
2015
abstract:
This paper focuses on the automatic extraction of domain-specific knowledge from the European Commission projects of the 7th Framework Programme, hereinafter referred as FP7. The study is divided in three parts: the first part introduces the work starting from the building up of a corpus containing the titles of European Projects of the whole FP7 in order to obtain a relevant terminological sample for the different domains; the second describes software and methods while the third part focuses on the evaluation of results. Finally, we conclude by suggesting possible directions for further development of a comparison between terminological extraction from FP7 and FP5/FP6.
Iris type:
04.01 Contributo in Atti di convegno
Keywords:
7th Framework Programme (FP7); Natural Language Processing; Terminology; Knowledge extraction; Grey Literature; I.2.7 Natural Language Processing. Text analysis; I.2.1 Applications and Expert Systems. Natural language interfaces
List of contributors: