Sentence Extraction by Graph Neural Networks

摘要

In this paper, we will apply a recently proposed connection-ist 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.