ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-02132018-112759


Tipo di tesi
Tesi di laurea magistrale
Autore
ALLEBOUDY, AHMAD SHAREEF MOSTAFA KAMEL
Indirizzo email
ahmad.alleboudy@outlook.com,ahmad.alleboudy@outlook.com
URN
etd-02132018-112759
Titolo
Deep learning for natural language processing of patent information
Dipartimento
INFORMATICA
Corso di studi
INFORMATICA
Relatori
relatore Bacciu, Davide
Parole chiave
  • Deep learning
  • ConvNets
  • IPC
  • Patent classification
Data inizio appello
02/03/2018
Consultabilità
Non consultabile
Data di rilascio
02/03/2088
Riassunto
Machine learning is crucial for providing intelligent features to text analytics platforms. In this respect, deep learning techniques have gained increasing interest in the natural language processing community in the latter years. Nevertheless, consolidated statistical models are still robust, cheaper, faster and easy to apply than deep learning models. In this thesis, the problem of analyzing textual descriptions of patents is approached by a mixture of deep learning and statistical models for word embeddings and text classification, embedding them into the Mergeflow AG analytics platform
File