Semantic distance and terminology structuring methods for the detection of semantically close terms

  • Authors:
  • Marie Dupuch;Thierry Hamo;Laëtitia Dupuch;Natalia Grabar

  • Affiliations:
  • Université Lille, France;Université Paris, France;Université Toulouse III Paul Sabatier, France;Université Lille, Villeneuve d'Ascq, France

  • Venue:
  • BioNLP '12 Proceedings of the 2012 Workshop on Biomedical Natural Language Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The identification of semantically similar linguistic expressions despite their formal difference is an important task within NLP applications (information retrieval and extraction, terminology structuring...) We propose to detect the semantic relatedness between biomedical terms from the pharmacovigilance area. Two approaches are exploited: semantic distance within structured resources and terminology structuring methods applied to a raw list of terms. We compare these methods and study their complementarity. The results are evaluated against the reference pharmacovigilance data and manually by an expert.