• deep learning
• generation
• machine learning
• natural language processing
• style analysis
• summarisation
• text generation

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.