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 exceptionally 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 easily reachable. In response, we propose DynaSemble, a novel method for learning query-dependent ensemble weights to combine these approaches by using the distributions of scores assigned by the models in the ensemble to all candidate entities. DynaSemble 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 the best baseline model for the WN18RR dataset.

翻译：知识图谱补全（KGC）领域存在两类主流方法：依赖文本实体描述的文本模型，以及利用知识图谱（KG）连通性结构的基于结构的模型。初步实验表明，这两类方法具有互补优势：当正确答案在知识图谱中易于从查询头实体到达时，基于结构的模型表现极为出色；而文本模型则能利用实体描述，即使在正确答案不易到达时仍能保持良好性能。为此，我们提出DynaSemble——一种通过学习查询依赖的集成权重来融合这两类方法的新颖方法，其权重计算利用了集成中各模型对所有候选实体赋予的分数分布。DynaSemble在三个标准KGC数据集上取得了最先进的结果，在WN18RR数据集上相比最佳基线模型实现了最高6.8个百分点的平均倒数排名（MRR）提升和8.3个百分点的Hits@1提升。