A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering

Knowledge Base Question Answering (KBQA) is a task where existing techniques have faced significant challenges, such as the need for complex question understanding, reasoning, and large training datasets. In this work, we demonstrate Deep Thinking (DTQA), semantic parsing reasoning-based KBQA system. DTQA (1) integrates multiple, reusable modules that are trained specifically their individual tasks (e.g. parsing, entity linking, relationship linking), eliminating end-to-end data; (2) leverages reasoner improved understanding. system of systems achieves state-of-the-art performance on two popular