This thesis investigates the role of context in the automatic aspect-based summarization of board game reviews. A two-stage approach is proposed: in the first stage, a Transformer-based model automatically identifies relevant aspects within the reviews; in the second stage, a generative model produces summaries that take into account different usage conditions, such as playing time, type of experience, and social setting.
CONTEXT-AWARE ASPECT-BASED SUMMARIZATION OF USER REVIEWS: A CASE STUDY IN THE BOARD GAME DOMAIN
ZAMPIERI, ROSSANA
2024/2025
Abstract
This thesis investigates the role of context in the automatic aspect-based summarization of board game reviews. A two-stage approach is proposed: in the first stage, a Transformer-based model automatically identifies relevant aspects within the reviews; in the second stage, a generative model produces summaries that take into account different usage conditions, such as playing time, type of experience, and social setting.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Tesi definitiva.pdf
non disponibili
Dimensione
3.36 MB
Formato
Adobe PDF
|
3.36 MB | Adobe PDF |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
Utilizza questo identificativo per citare o creare un link a questo documento:
https://hdl.handle.net/20.500.14253/64133