Violence detection explanation via semantic roles embeddings

Enrico Mensa; Davide Colla; Marco Dalmasso; Marco Giustini; Carlo Mamo; Alessio Pitidis; Daniele P. Radicioni

doi:10.1186/s12911-020-01237-4

Violence detection explanation via semantic roles embeddings

Enrico Mensa, Davide Colla, Marco Dalmasso, Marco Giustini, Carlo Mamo, Alessio Pitidis, Daniele P. Radicioni

Istituto Superiore di Sanita'

Research output: Contribution to journal › Article › peer-review

Abstract

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.

Original language	English
Journal	BMC Medical Informatics and Decision Making
Volume	20
Issue number	1
DOIs	https://doi.org/10.1186/s12911-020-01237-4
Publication status	Published - 2020

Access to Document

10.1186/s12911-020-01237-4

Cite this

@article{9a8db9d6074743b3a4cac6814fc2457e,

title = "Violence detection explanation via semantic roles embeddings",

abstract = "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.",

author = "Enrico Mensa and Davide Colla and Marco Dalmasso and Marco Giustini and Carlo Mamo and Alessio Pitidis and Radicioni, {Daniele P.}",

year = "2020",

doi = "10.1186/s12911-020-01237-4",

language = "English",

volume = "20",

journal = "BMC Medical Informatics and Decision Making",

issn = "1472-6947",

publisher = "BioMed Central",

number = "1",

}

TY - JOUR

T1 - Violence detection explanation via semantic roles embeddings

AU - Mensa, Enrico

AU - Colla, Davide

AU - Dalmasso, Marco

AU - Giustini, Marco

AU - Mamo, Carlo

AU - Pitidis, Alessio

AU - Radicioni, Daniele P.

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

U2 - 10.1186/s12911-020-01237-4

DO - 10.1186/s12911-020-01237-4

M3 - Article

SN - 1472-6947

VL - 20

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

IS - 1

ER -

Violence detection explanation via semantic roles embeddings

Abstract

Access to Document

Fingerprint

Cite this