论文标题
通过相对位置对图形生成的相对位置进行建模，从知识图
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs
论文作者
论文摘要
我们提出了Graformer，这是一种基于变压器的新型编码器架构，用于图形到文本生成。借助我们新颖的图形自我注意，对节点的编码依赖于输入图中的所有节点 - 不仅是直接的邻居 - 促进了全局模式的检测。我们表示两个节点之间的关系是它们之间最短路径的长度。 Graformer学会了对不同注意力头的不同对这些节点节点的关系的加权，从而实际上学习了输入图的不同联系的视图。我们在两个流行的图形到文本生成基准（议程和WebNLG）上评估了Graformer，它在其中实现了强劲的性能，同时使用的参数少于其他方法。
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating the detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.
