.png){kind=icon}
返回
Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00269.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation. To capture structural information associated with graphs, we investigate the problem of encoding graphs using graph convolutional networks (GCNs). Unlike various existing approaches where shallow architectures were used for capturing local structural information only, we introduce a dense connection strategy, proposing a novel Densely Connected Graph Convolutional Network (DCGCN). Such a deep architecture is able to integrate both local and non-local features to learn a better structural representation of a graph. Ourmodel outperforms the state-of-the-art neural models significantly on AMR-to-text generation and syntax-based neural machine translation.
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
.png){kind=icon}
