We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG). Preliminary experiments show that these approaches have complementary strengths: structure-based models perform well when the gold answer is easily reachable from the query head in the KG, while textual models exploit descriptions to give good performance even when the gold answer is not reachable. In response, we explore ensembling as a way of combining the best of both approaches. We propose a novel method for learning query-dependent ensemble weights by using the distributions of scores assigned by individual models to all candidate entities. Our ensemble baseline achieves state-of-the-art results on three standard KGC datasets, with up to 6.8 pt MRR and 8.3 pt Hits@1 gains over best individual models.

翻译：我们研究了知识图谱补全（KGC）的两种主流方法：依赖文本实体描述的文本模型，以及利用知识图谱（KG）连接结构的结构模型。初步实验表明，这两种方法具有互补优势：当正确答案在知识图谱中可从查询头部轻松到达时，结构模型表现良好；而文本模型通过利用实体描述，即使正确答案无法到达也能取得优异性能。为此，我们探索使用集成方法结合两者的优势。我们提出了一种新颖的方法，通过利用各模型对所有候选实体的得分分布来学习查询相关的集成权重。我们的集成基线在三个标准KGC数据集上取得了最先进的结果，相较于最优单模型，平均倒数排名（MRR）提升达6.8个百分点，Hits@1指标提升达8.3个百分点。