Fusion of Heterogeneous Information in Graph-Based Ranking for Query-Biased Summarization

We propose a graph-based ranking method for query-biased summarization in a three-layer graph model consisting of document, sentence and word-layers. The model has a representation that fuses three kinds of heterogeneous information: part-whole relationships between different linguistic units, similarity using the overlap of the Basic Elements (BEs) in the statements, and semantic similarity between words. In an experiment using the text summarization test collection of Nakano et al., our proposed method achieved the best result of the five considered methods, which were based on other graph models with an average R-Precision of 0.338.