Violence detection explanation via semantic roles embeddings.

Journal: BMC medical informatics and decision making
Published Date: Oct 15, 2020

Abstract

BACKGROUND: Emergency room reports pose specific challenges to natural language processing techniques. In this setting, violence episodes on women, elderly and children are often under-reported. Categorizing textual descriptions as containing violence-related injuries (V) vs. non-violence-related injuries (NV) is thus a relevant task to the ends of devising alerting mechanisms to track (and prevent) violence episodes.

Authors

  • Enrico Mensa
    Department of Computer Science, University of Turin, Corso Svizzera 185, Turin, 10149, Italy.
  • Davide Colla
    Department of Computer Science, University of Turin, Corso Svizzera 185, Turin, 10149, Italy.
  • Marco Dalmasso
    Servizio sovrazonale di Epidemiologia dell'ASL TO3 della Regione Piemonte, Via Sabaudia 164, Grugliasco (TO), 10095, Italy.
  • Marco Giustini
    Reparto Epidemiologia ambientale e sociale Dipartimento Ambiente e Salute (DAMSA) Istituto Superiore di Sanità, Viale Regina Elena, 299, Roma, 00161, Italy.
  • Carlo Mamo
    Servizio sovrazonale di Epidemiologia dell'ASL TO3 della Regione Piemonte, Via Sabaudia 164, Grugliasco (TO), 10095, Italy.
  • Alessio Pitidis
    Reparto Epidemiologia ambientale e sociale Dipartimento Ambiente e Salute (DAMSA) Istituto Superiore di Sanità, Viale Regina Elena, 299, Roma, 00161, Italy.
  • Daniele P Radicioni
    Department of Computer Science, University of Turin, Corso Svizzera 185, Turin, 10149, Italy. daniele.radicioni@unito.it.

Keywords

External Resources

Popular Topics
Recent Journals