Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering
This addresses the challenge of answering complex questions that require information from multiple sources, offering an incremental improvement in explainable QA.
The paper tackles the problem of integrating heterogeneous knowledge sources for explainable question answering by decomposing complex questions into simpler sub-questions and using a hierarchical tree structure for probabilistic reasoning. It reports significant outperformance over state-of-the-art methods on datasets like KQA Pro and Musique.
Explainable question answering (XQA) aims to answer a given question and provide an explanation why the answer is selected. Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured corpora, etc. However, integrating information from heterogeneous knowledge sources is essential to answer complex questions. In this paper, we propose to leverage question decomposing for heterogeneous knowledge integration, by breaking down a complex question into simpler ones, and selecting the appropriate knowledge source for each sub-question. To facilitate reasoning, we propose a novel two-stage XQA framework, Reasoning over Hierarchical Question Decomposition Tree (RoHT). First, we build the Hierarchical Question Decomposition Tree (HQDT) to understand the semantics of a complex question; then, we conduct probabilistic reasoning over HQDT from root to leaves recursively, to aggregate heterogeneous knowledge at different tree levels and search for a best solution considering the decomposing and answering probabilities. The experiments on complex QA datasets KQA Pro and Musique show that our framework outperforms SOTA methods significantly, demonstrating the effectiveness of leveraging question decomposing for knowledge integration and our RoHT framework.