作者: Andrea Giovanni Nuzzolese , Silvio Peroni , Diego Reforgiato Recupero
DOI: 10.1007/978-3-319-46565-4_22
关键词:
摘要: This paper presents the Article Content Miner (a.k.a. ACM), i.e., a method for processing research papers in PDF format available 2016 edition of Semantic Publishing Challenge order to extract relevant semantic data and publish them RDF triplestore according And Referencing (SPAR) Ontologies (http://www.sparontologies.net). In particular, extraction all information needed addressing queries second task challenge (https://github.com/ceurws/lod/wiki/SemPub16_Task2) is guaranteed by ACM using techniques based on Natural Language Processing (i.e., Combinatory Categorial Grammar, Discourse Representation Theory, Linguistic Frames), Web technologies good Ontology Design practices Analysis, Patterns, Referent Extraction Linking, Topic Extraction).