logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-04092020-120722


Tipo di tesi
Tesi di laurea magistrale
Autore
OCCHIPINTI, DANIELA
URN
etd-04092020-120722
Titolo
Industrial Strength Multilingual Named Entity Collection for the SPIRIT Project
Dipartimento
FILOLOGIA, LETTERATURA E LINGUISTICA
Corso di studi
INFORMATICA UMANISTICA
Relatori
relatore Prof. Romani, Francesco
correlatore Dott. De Mattei, Lorenzo
controrelatore Prof.ssa Simi, Maria
Parole chiave
  • Deep Learning
  • Microservices Architecture
  • Named Entity Recognition
  • Natural Language Processing
  • Open Domain
  • OSINT
Data inizio appello
27/04/2020
Consultabilità
Non consultabile
Data di rilascio
27/04/2090
Riassunto
Scalable privacy preserving intelligence analysis for resolving identities (SPIRIT) is a Cybersecurity and OSINT project which has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 786993. The SPIRIT Project aims to provide an innovative platform based on an integrated approach for the multimodal and multilingual analysis of different types of content from different types of sources in order to facilitate cognitive tasks in the resolution of criminal identities. In the present work we give a detailed overview of the SPIRIT platform's architecture and pipelines, showing the entire technological stack. Then, we will shift the attention to the NLP and Deep Learning techniques adopted and the experiments conducted in order to provide a performing Multilingual Open Domain Named Entity Recognition engine.
File