知识是扁平的：一个Seq2Seq生成框架用于各种知识图谱的补全
Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion
摘要：
近年来，知识图补全（Knowledge Graph Completion，KGC）被扩展到多个知识图谱结构，引发了新的研究方向，如静态知识图补全、时态知识图补全和少镜头知识图补全（Few-Shot）。以往的KGC模型往往与特定的图结构紧密耦合，这必然导致两个缺陷：1）特定结构的KGC模型互不兼容; 2）现有的KGC方法对新兴的KGs不适应。在本文中，我们提出了KG-S2 S，这是一个Seq 2Seq生成框架，可以通过将KG事实的表示统一为“平面”文本来处理不同的可动词化的图形结构，而不管它们的原始形式如何。为了弥补“平面”文本造成的KG结构信息丢失，进一步改进了KG-S2 S中实体和关系的输入表示以及推理算法。在五个基准测试上的实验表明，KG-S2 S的性能优于许多竞争对手的基线，创造了新的最先进的性能。最后分析了KG-S2 S在不同关系和非实体生成上的能力。
英文摘要：
Knowledge Graph Completion (KGC) has been recently extended to multiple knowledge graph (KG) structures, initiating new research directions, e.g. static KGC, temporal KGC and few-shot KGC. Previous works often design KGC models closely coupled with specific graph structures, which inevitably results in two drawbacks: 1) structure-specific KGC models are mutually incompatible; 2) existing KGC methods are not adaptable to emerging KGs. In this paper, we propose KG-S2S, a Seq2Seq generative framework that could tackle different verbalizable graph structures by unifying the representation of KG facts into "flat" text, regardless of their original form. To remedy the KG structure information loss from the "flat" text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S. Experiments on five benchmarks show that KG-S2S outperforms many competitive baselines, setting new state-of-the-art performance. Finally, we analyze KG-S2S's ability on the different relations and the Non-entity Generations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
