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 \citep{mintz-etal-2009-distant}. 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.
@article{arxiv.2109.06046,
title = {Augmented Abstractive Summarization With Document-LevelSemantic Graph},
author = {Qiwei Bi and Haoyuan Li and Kun Lu and Hanfang Yang},
journal= {arXiv preprint arXiv:2109.06046},
year = {2021}
}