A knowledge base is a large repository of facts usually represented as triples, each consisting of a subject, a predicate, and an object. The triples together form a graph, i.e., a knowledge graph. The triple representation in a knowledge graph offers a simple interface for applications to access the facts. However, this representation is not in a natural language form, which is difficult for humans to understand. We address this problem by proposing a system to translate a set of triples (i.e., a graph) into natural sentences. We take an encoder-decoder based approach. Specifically, we propose a Graph encoder with Content-Planning capability (GCP) to encode an input graph. GCP not only works as an encoder but also serves as a content-planner by using an entity-order aware topological traversal to encode a graph. This way, GCP can capture the relationships between entities in a knowledge graph as well as providing information regarding the proper entity order for the decoder. Hence, the decoder can generate sentences with a proper entity mention ordering. Experimental results show that GCP achieves improvements over state-of-the-art models by up to 3.6%3.6\%, 4.1%4.1\%, and 3.8%3.8\% in three common metrics BLEU, METEOR, and TER, respectively. The code is available at (https://github.com/ruizhang-ai/GCP/)

中文翻译：

---

GCP：具有内容规划功能的图形编码器，用于从知识库生成句子


知识库是一个大型事实存储库，通常表示为三元组，每个三元组由主语、谓语和宾语组成。三元组一起形成一个图，即知识图。知识图中的三重表示为应用程序访问事实提供了一个简单的界面。然而，这种表示并不是自然语言形式，人类很难理解。我们通过提出一个将一组三元组（即图）翻译成自然句子的系统来解决这个问题。我们采用基于编码器-解码器的方法。具体来说，我们提出了一种具有内容规划功能（GCP）的图编码器来对输入图进行编码。 GCP 不仅充当编码器，还通过使用实体顺序感知拓扑遍历来编码图来充当内容规划器。这样，GCP 就可以捕获知识图中实体之间的关系，并为解码器提供有关正确实体顺序的信息。因此，解码器可以生成具有正确实体提及排序的句子。实验结果表明，GCP 在 BLEU、METEOR 和 TER 三个常用指标上分别比最先进的模型提高了 3.6%3.6\%、4.1%4.1\% 和 3.8%3.8\%。代码可在（https://github.com/ruizhang-ai/GCP/）获取