Final: Combining First-Order Logic With Natural Logic for Question Answering

Many question-answering problems can be approached as textual entailment tasks, where the hypotheses are formed by the question and candidate answers, and the premises are derived from an external knowledge base. However, current neural methods often lack transparency in their decision-making processes. Moreover, first-order logic methods, while systematic, struggle to integrate unstructured external knowledge. To address these limitations, we propose a neuro-symbolic reasoning framework called Final, which combines FIrst-order logic with NAtural Logic for question answering. Our framework utilizes first-order logic to systematically decompose hypotheses and natural logic to construct reasoning paths from premises to hypotheses, employing bidirectional reasoning to establish links along the reasoning path. This approach not only enhances interpretability but also effectively integrates unstructured knowledge. Our experiments on three benchmark datasets, namely QASC, WorldTree, and WikiHop, demonstrate that Final outperforms existing methods in commonsense reasoning and reading comprehension tasks, achieving state-of-the-art results. Additionally, our framework also provides transparent reasoning paths that elucidate the rationale behind the correct decisions.