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

Authors

  • Ibrahim Abdelaziz IBM Research
  • Srinivas Ravishankar IBM Research
  • Pavan Kapanipathi IBM Research
  • Salim Roukos IBM Research
  • Alexander Gray IBM Research

DOI:

https://doi.org/10.1609/aaai.v35i18.17988

Keywords:

KBQA, Semantic Parsing, Neuro-symbolic, Reasoning, Question Answering, Semantic Web

Abstract

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 Question Answering (DTQA), a semantic parsing and reasoning-based KBQA system. DTQA (1) integrates multiple, reusable modules that are trained specifically for their individual tasks (e.g. semantic parsing, entity linking, and relationship linking), eliminating the need for end-to-end KBQA training data; (2) leverages semantic parsing and a reasoner for improved question understanding. DTQA is a system of systems that achieves state-of-the-art performance on two popular KBQA datasets.

Downloads

Published

2021-05-18

How to Cite

Abdelaziz, I., Ravishankar, S., Kapanipathi, P., Roukos, S., & Gray, A. (2021). A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15985-15987. https://doi.org/10.1609/aaai.v35i18.17988