In this paper, we will apply a recently proposed connectionist model, namely, the Graph Neural Network, for processing the graph formed by considering each sentence in a document as a node and the relationship between two sentences as an edge. Using commonly accepted evaluation protocols, the ROGUE toolkit, the technique was applied to two text summarization benchmarks, namely DUC-2001 and DUC-2002 respectively. It is found that the results obtained are comparable to the best results achieved using other techniques.
Muratore, D., Hagenbuchner, M., Scarselli, F., Tsoi, A.C. (2010). Sentence Extraction by Graph Neural Networks. In Proceedings of 20th International Conference on Artificial Neural Networks (ICANN 2010) (pp.237-246). Spinger [10.1007/978-3-642-15825-4_29].
Sentence Extraction by Graph Neural Networks
Scarselli F.;
2010-01-01
Abstract
In this paper, we will apply a recently proposed connectionist model, namely, the Graph Neural Network, for processing the graph formed by considering each sentence in a document as a node and the relationship between two sentences as an edge. Using commonly accepted evaluation protocols, the ROGUE toolkit, the technique was applied to two text summarization benchmarks, namely DUC-2001 and DUC-2002 respectively. It is found that the results obtained are comparable to the best results achieved using other techniques.
| File | Dimensione | Formato | |
|---|---|---|---|
|
ICANN2010 sentence extraction.pdf
non disponibili
Tipologia:
Post-print
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
175.94 kB
Formato
Adobe PDF
|
175.94 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/18198
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo