Sentence extraction by graph neural networks

Authors

Donatella Muratore, University of Siena
Markus Hagenbuchner, University of WollongongFollow
Franco Scarselli, University of Siena
Ah Chung Tsoi, Hong Kong Baptist UniversityFollow

RIS ID

34613

Publication Details

Muratore, D., Hagenbuchner, M., Scarselli, F. & Tsoi, A. (2010). Sentence extraction by graph neural networks. K. Diamantaras, W. Duck & L. S. Iliadis In Artificial Neural Networks-ICANN 2010: 20th International Conference, 15-18 Sep 2010, Greece. LNCS, 6354 237-246.

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.