Name
Abstract | ||
|---|---|---|
Sequence to sequence (Seq2Seq) model for abstractive summarization have aroused widely attention due to their powerful ability to represent sequence. However, the sequence structured data is a simple format, which cannot describe the complexity of graphs and may lead to ambiguous, and hurt the performance of summarization. In this paper, we propose a Gated Graph Neural Attention Networks (GGNANs) for abstractive summarization. The proposed GGNANs unified graph neural network and the celebrated Seq2seq for better encoding the full graph-structured information. We propose a graph transform method based on PMI, self-connection, forward-connection and backward-connection to better combine graph-structured information and the sequence-structured information. Extensive experimental results on the LCSTS and Gigaword show that our proposed model outperforms most of strong baseline models. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.neucom.2020.09.066 | Neurocomputing |
Keywords | DocType | Volume |
Seq2Seq,Abstractive summarization,Gated Graph Neural Attention Networks | Journal | 431 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zeyu Liang | 1 | 0 | 0.68 |
| Junping Du | 2 | 789 | 91.80 |
| Yingxia Shao | 3 | 213 | 24.25 |
| Houye Ji | 4 | 5 | 2.46 |