logo SBA

ETD

Digital archive of theses discussed at the University of Pisa

 

Thesis etd-05302018-110802

Link copiato negli appunti
Thesis type
Tesi di laurea magistrale
URN
etd-05302018-110802
Thesis title
POS-tagging improvement for patent analysis: from theory to practice
Department
INGEGNERIA DELL'ENERGIA, DEI SISTEMI, DEL TERRITORIO E DELLE COSTRUZIONI
Course of study
INGEGNERIA GESTIONALE
Keywords
  • blockchain
  • chunk extraction
  • improvement
  • named entity recognition
  • Natural language processing
  • patents
  • POS-tagging
  • POS-tagging analysis
Graduation session start date
20/06/2018
Availability
Withheld
Release date
20/06/2088
Abstract (Inglese)
Abstract (Italiano)
The thesis consists of the POS-tagging analysis in order to reduce or eliminate the errors made by the POS-tagger itself. The process is composed by an initial and manual analysis and research of proposals of substitutive tokens or effective text improvements. The proposals are applied to a data set of patents concerning the blockchain: the results are analyzed checking the results of two NLP tasks: chunk extraction and named entity recognition.
File
Nome file Dimensione
Thesis not available for consultation.
Contatta l'autore