Evaluating the Quality of the Indonesian Scientific Journal References using ParsCit, CERMINE and GROBID

Evaluating the Quality of the Indonesian Scientific Journal References using ParsCit, CERMINE and GROBID

Keywords:Automatic extraction bibliography, Indonesian scientific journals, open-source tools, application architecture
Abstract:Evaluating the Quality of the Indonesian Scientific Journal References using ParsCitCERMINE and GROBID There are several open-source tools available to extract the bibliographic references of the PdfThose tools based on the various approaches including rule-based approachknowledge-based approachmachine learning-based approachand the combinationTo improve the services of the Indonesian Scientific Journal DatabaseISJDCenter for Scientific Data and DocumentationIndonesian Institute of SciencesPDDI-LIPIintends to have an automatic bibliographic references extraction toolThe paper aims to analyze the quality of the reference metadata of the local journals with the three open-source toolsnamely ParsCitCERMINE and GROBIDThe accuracy test of the three tools are poorThose are 05550633and 0605 for ParsCitCERMINEand GROBID respectivelyIt caused by many authors do not use a reference manager when they write the bibliography sectionOn the such condition this paper proposed to build an application to identify and correct errors in the bibliographic references of paper in ISJDThis application become a liaison between ISJD and open source tool for the bibliographic reference extractionThis paper proposed the combination of building software and using an open source Retrieval and IndexingBecause this technology is used to automatically extract literature reference materialsit can help optimize the process of retrieval and indexThe focus of this article is to use the open source tool to extract literature reference materials from the PDFwhich involves the processing and analysis of textso it belongs to the category of natural language processingNLP