Summary of the paper

Title Wikipedia-based Approach for Linking Ontology Concepts to their Realisations in Text
Authors Giulio Paci, Giorgio Pedrazzi and Roberta Turra
Abstract A novel method to automatically associate ontological concepts to theirrealisations in texts is presented. The method has been developed in thecontext of the Papyrus project to annotate texts and audio transcripts with aset of relevant concepts from the Papyrus News Ontology. To avoid strongdependency on a specific ontology, the annotation process starts by performinga Wikipedia-based annotation of news items: the most relevant keywords aredetected and the Wikipedia pages that best describe their actual meaning areidentified. In a later step this annotation is translated into anOntology-based one: keywords are connected to the most appropriate ontologyclasses on the basis of a relatedness measure that relies on Wikipediaknowledge. Wikipedia-annotation provides a domain independent abstraction layerthat simplify the adaptation of the approach to other domains and ontologies.Evaluation has been performed on a set of manually annotated news, resulting in58% F1 score for relevant Wikipedia pages and 64% for relevant ontologyconcepts identification.
Language Summarisation
Topics Text mining, Ontologies, Summarisation
Full paper Wikipedia-based Approach for Linking Ontology Concepts to their Realisations in Text
Bibtex @InProceedings{PACI10.132,
  author = {Giulio Paci, Giorgio Pedrazzi and Roberta Turra},
  title = {Wikipedia-based Approach for Linking Ontology Concepts to their Realisations in Text},
  booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
  year = {2010},
  month = {may},
  date = {19-21},
  address = {Valletta, Malta},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-6-7},
  language = {english}
 }
Powered by ELDA © 2010 ELDA/ELRA