2021 年 28 巻 2 号 p. 651-676
Modeling the relations between text spans in a document is a crucial yet challenging problem for extractive summarization. Various kinds of relations exist among text spans of different granularity, such as discourse relations between elementary discourse units and coreference relations between phrase mentions. In this paper, we utilize heterogeneous graphs that contain multiple edge/node types to model the input document as well as the various relations among text spans in it. Also, we propose a heterogeneous graph based model for extractive summarization that considers the heterogeneity of the document graph. Experimental results on a benchmark summarization dataset verify the effectiveness of our proposed method.
