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.

信息检索中的知识图谱问答方法包括两个阶段：子图提取和答案推理。我们认为当前的子图提取方法低估了证据事实之间的结构依赖的重要性。我们提出了证据模式检索（EPR）来在子图提取过程中明确地建模结构依赖关系。通过对资源对的原子相邻模式进行索引，我们实现了 EPR。给定一个问题，我们进行密集检索，以获取由资源对形成的原子模式。然后，我们枚举它们的组合来构造候选证据模式。使用神经模型对这些证据模式进行评分，并选择最佳模式来提取下游答案推理所需的子图。实验结果表明，基于 EPR 的方法显著提高了在 ComplexWebQuestions 上 IR-KGQA 方法的 F1 得分，且在 WebQuestionsSP 上取得了竞争性的性能。