ETD system

Electronic theses and dissertations repository

 

Tesi etd-09192019-085220


Thesis type
Tesi di laurea magistrale
Author
CAFAGNA, MICHELE
URN
etd-09192019-085220
Title
Headline Generation and Analysis of Writing Styles in Journalism
Struttura
INFORMATICA
Corso di studi
INFORMATICA
Supervisors
relatore Prof. Bacciu, Davide
relatore Prof.ssa Nissim, Malvina
Parole chiave
  • natural language processing
  • text generation
  • generation
  • summarisation
  • deep learning
  • machine learning
  • style analysis
Data inizio appello
04/10/2019;
Consultabilità
Secretata d'ufficio
Riassunto analitico
The thesis deal with generative language models in the journalism domain, focusing on headline generation and style transfer on Italian newspapers. The work covers all the natural language processing pipeline, from the data collection to the human evaluation and it proposes a method to study the stylistic aspects looking at the embeddings shift and it investigates on style transfer, experimenting various approaches.
File