ACM: Article content miner for assessing the quality of scientific output

Abstract

This paper presents the Article Content Miner (a.k.a. ACM), i.e., a method for processing the research papers in PDF format available for the 2016 edition of the Semantic Publishing Challenge in order to extract relevant semantic data and publish them in a RDF triplestore according to the Semantic Publishing And Referencing (SPAR) Ontologies (http://www.sparontologies.net). In particular, the extraction of all the information needed for addressing the queries of the second task of the challenge (https://github.com/ceurws/lod/wiki/SemPub16 Task2) is guaranteed by ACM by using techniques based on Natural Language Processing (i.e., Combinatory Categorial Grammar, Discourse Representation Theory, Linguistic Frames), Semantic Web technologies and good Ontology Design practices (i.e., Content Analysis, Ontology Design Patterns, Discourse Referent Extraction and Linking, Topic Extraction).