Information retrieval (IR) methods for KGQA consist of two stages: subgraph extraction and answer reasoning. We argue current subgraph extraction methods underestimate the importance of structural dependencies among evidence facts. We propose Evidence Pattern Retrieval (EPR) to explicitly model the structural dependencies during subgraph extraction. We implement EPR by indexing the atomic adjacency pattern of resource pairs. Given a question, we perform dense retrieval to obtain atomic patterns formed by resource pairs. We then enumerate their combinations to construct candidate evidence patterns. These evidence patterns are scored using a neural model, and the best one is selected to extract a subgraph for downstream answer reasoning. Experimental results demonstrate that the EPR-based approach has significantly improved the F1 scores of IR-KGQA methods by over 10 points on ComplexWebQuestions and achieves competitive performance on WebQuestionsSP.

翻译：信息检索（IR）方法在知识图谱问答（KGQA）中通常包含两个阶段：子图提取与答案推理。我们认为现有子图提取方法低估了证据事实间结构依赖性的重要性。本文提出证据模式检索（EPR）方法，以显式建模子图提取过程中的结构依赖性。EPR通过索引资源对的原子邻接模式实现：针对给定问题，采用稠密检索获取资源对构成的原子模式，随即枚举其组合以构建候选证据模式。这些证据模式通过神经模型进行评分，选择最优模式提取子图供下游答案推理使用。实验结果表明，基于EPR的方法在ComplexWebQuestions数据集上将IR-KGQA方法的F1分数提升超过10个百分点，并在WebQuestionsSP数据集上取得具有竞争力的性能表现。