期刊
TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS
卷 7, 期 -, 页码 297-312出版社
MIT PRESS
DOI: 10.1162/tacl_a_00269
关键词
-
资金
- Singapore Ministry of Education Academic Research Fund (AcRF) Tier 2 Project [MOE2017T2-1-156]
- SUTD project [PIE-SGP-AI-2018-01]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据