English

Augmented Abstractive Summarization With Document-LevelSemantic Graph

Computation and Language 2021-09-14 v1

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 \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.

Keywords

Cite

@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}
}

Comments

Accepted to Journal of Data Science