[Publication Time] 2021-05-04

[Lead Author] 毕启炜

[Corresponding Author] 杨翰方

[Journal] Journal of Data Science

[Abstract]

Previous abstractive methods apply sequence-to-sequence structures to generate summary without a module to assist the system to detect vital mentions and relationships within a document. To address this problem, we utilize semantic graph to boost the generation performance. Firstly, we extract important entities from each document and then establish a graph inspired by the idea of distant supervision (Mintz et al., 2009). Then, we combine a Bi-LSTM with a graph encoder to obtain the representation of each graph node. A novel neural decoder is presented to leverage the information of such entity graphs. Automatic and human evaluations show the effectiveness of our technique.

[Keywords]

entity extraction；information extraction； distant supervise； graph attention neural；network