在知识库问答中更加关注关系探索
Pay More Attention to Relation Exploration for Knowledge Base Question Answering
AI总结：
本文提出 RE-KBQA 框架，通过关系重要性学习、关系分布预测和关系引导重排序三种方式增强知识库问答中的关系探索，在 CWQ 和 WebQSP 上显著提升 F1 分数。
摘要：
知识库问答（KBQA）是一项具有挑战性的任务，旨在从大规模知识库中检索正确答案。现有方法主要关注实体表示和最终答案推理，导致该任务的监督信号有限。此外，关系在经验上决定了推理路径的选择，但在近期进展中并未得到充分考虑。在本研究中，我们提出了一个新颖的框架 RE-KBQA，利用知识库中的关系来增强实体表示并引入额外的监督。我们从三个方面探索关系的指导作用，包括：（1）通过采用变分图自编码器学习关系重要性来区分相似实体；（2）通过多任务方案预测关系分布作为软标签来探索额外监督；（3）设计一种关系引导的重排序算法用于后处理。在两个基准数据集上的实验结果表明了我们框架的有效性和优越性，在 CWQ 上 F1 分数从 40.5 提高到 46.3，提升了 5.7%，在 WebQSP 上从 62.8 提高到 68.5，提升了 5.8%，优于或持平于最先进的方法。
英文摘要：
Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, which empirically determine the reasoning path selection, are not fully considered in recent advancements. In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision. We explore guidance from relations in three aspects, including (1) distinguishing similar entities by employing a variational graph auto-encoder to learn relation importance; (2) exploring extra supervision by predicting relation distributions as soft labels with a multi-task scheme; (3) designing a relation-guided re-ranking algorithm for post-processing. Experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our framework, improving the F1 score by 5.7% from 40.5 to 46.3 on CWQ and 5.8% from 62.8 to 68.5 on WebQSP, better or on par with state-of-the-art methods.
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。
