arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.02175cs.CLcs.IR
收藏

通过证据模式检索增强知识图谱上的复杂问答

Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval

State Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室)

Wentao Ding, Jinmao Li, Liangchuan Luo, Yuzhong Qu

AI总结:

本文提出证据模式检索(EPR)方法,通过显式建模知识图谱问答中子图提取的结构依赖性,显著提升复杂问答的F1分数。

摘要:

用于知识图谱问答(KGQA)的信息检索(IR)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结构依赖性的重要性。我们提出证据模式检索(EPR)来在子图提取过程中显式建模结构依赖性。我们通过索引资源对的原子邻接模式来实现EPR。给定一个问题,我们执行密集检索以获得由资源对形成的原子模式。然后我们枚举它们的组合以构建候选证据模式。这些证据模式使用神经模型进行评分,并选择最佳模式来提取子图用于下游答案推理。实验结果表明,基于EPR的方法在ComplexWebQuestions上将IR-KGQA方法的F1分数显著提高了超过10个百分点,并在WebQuestionsSP上取得了有竞争力的性能。

英文摘要:

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.

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。

↑