A Complex KBQA System using Multiple Reasoning Paths

TL;DR

This paper presents an end-to-end KBQA system that leverages multiple reasoning paths without needing labeled paths, improving performance on complex multi-hop questions across various benchmark datasets.

Contribution

Introduces a novel KBQA approach that utilizes multiple reasoning paths with only answer supervision, bypassing the need for labeled reasoning paths.

Findings

Strong performance on benchmark datasets

Effective handling of multi-hop complex questions

Outperforms existing KBQA systems

Abstract

Multi-hop knowledge based question answering (KBQA) is a complex task for natural language understanding. Many KBQA approaches have been proposed in recent years, and most of them are trained based on labeled reasoning path. This hinders the system's performance as many correct reasoning paths are not labeled as ground truth, and thus they cannot be learned. In this paper, we introduce an end-to-end KBQA system which can leverage multiple reasoning paths' information and only requires labeled answer as supervision. We conduct experiments on several benchmark datasets containing both single-hop simple questions as well as muti-hop complex questions, including WebQuestionSP (WQSP), ComplexWebQuestion-1.1 (CWQ), and PathQuestion-Large (PQL), and demonstrate strong performance.