Event extraction using ontology directed semantic grammar

Simple item page
dc.contributor.authorKuptabut, Suthasinee
dc.contributor.authorNetisopakul, Ponrudee
dc.date.accessioned2026-08-06T10:13:11Z
dc.date.available2026-08-06T10:13:11Z
dc.date.issued2016-01-01
dc.description.abstractThe task of extracting and constructing knowledge base from news is still a subject of ongoing research. The obtained knowledge base is useful for many applications, such as a question answering system. Football news always gains enormous interest from many football fan clubs. Hence, there are needs to extract certain information from this news in timely fashion. This paper proposes a new approach to extract football events from football news webpages and represents them as frames. One of the main contributions of the new approach is the process of dynamically generating semantic grammar from football domain ontology. A semantic parser uses this grammar to recognize events of interest and their details. This paper explains the overall architecture of our system called Ontology Directed Event Extraction System and explains detail implementation of our new proposed approach for extracting football events. The system is demonstrated by extracting events from 40 football news webpages, resulting in 699 frames which evaluated over 85% precision and recall.
dc.identifier.citationJournal of Information Science and Engineering, 32(1), 79-96, 2016
dc.identifier.issn10162364
dc.identifier.other2-s2.0-84954113900
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/6692
dc.sourceJournal of Information Science and Engineering
dc.subjectEvent Extraction
dc.subjectFrame integration
dc.subjectInference rules
dc.subjectOntology
dc.subjectSemantic parser
dc.titleEvent extraction using ontology directed semantic grammar
dc.typeArticle

Files

Collections

Research