Istex: A Database of Twenty Million Scientific Papers with a Mining Tool Which Uses Named Entities

Information

Nicolas Thouvenin¹  Enza Morale¹  Angel Turri¹  Denis Maurel²  Patrice Ringot³ 

[1] Institut de l’Information Scientifique et Technique, 54500 Nancy, France;Laboratoire d’Informatique Fondamentale et Appliquée de Tours (LIFAT), Université de Tours, 37000 Tours, France;Lorraine Research Laboratory in Computer Science and Its Applications (Loria), Université de Lorraine, 54506 Nancy, France;

关键词: text mining;    named entity recognition;    data base of scientific papers;    Istex;    Unitex;    CasEN;    Docker;   

DOI  :  10.3390/info10050178

来源: DOAJ

【 摘 要 】

Istex is a database of twenty million full text scientific papers bought by the French Government for the use of academic libraries. Papers are usually searched for by the title, authors, keywords or possibly the abstract. To authorize new types of queries of Istex, we implemented a system of named entity recognition on all papers and we offer users the possibility to run searches on these entities. After the presentation of the French Istex project, we detail in this paper the named entity recognition with CasEN, a cascade of graphs, implemented on the Unitex Software. CasEN exists in French, but not in English. The first challenge was to build a new cascade in a short time. The results of its evaluation showed a good Precision measure, even if the Recall was not very good. The Precision was very important for this project to ensure it did not return unwanted papers by a query. The second challenge was the implementation of Unitex to parse around twenty millions of documents. We used a dockerized application. Finally, we explain also how to query the resulting Named entities in the Istex website.

【 授权许可】

Unknown