Pay More Attention to Relation Exploration for Knowledge Base Question Answering
This work addresses a bottleneck in KBQA for improving accuracy in retrieving answers from knowledge bases, representing an incremental advancement with specific gains.
The paper tackles the problem of limited supervision and underutilized relations in knowledge base question answering (KBQA) by proposing a novel framework, RE-KBQA, which enhances entity representation and introduces additional supervision through relation exploration, resulting in F1 score improvements of 5.7% on CWQ and 5.8% on WebQSP datasets.
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.