Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Abstract
Knowledge base question answering (KBQA)is an important task in Natural Language Processing. Existing approaches face significant challenges including complex question understanding, necessity for reasoning, and lack of large end-to-end training datasets. In this work, we propose Neuro-Symbolic Question Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning Representation (AMR) parses for task-independent question understanding; (2) a simple yet effective graph transformation approach to convert AMR parses into candidate logical queries that are aligned to the KB; (3) a pipeline-based approach which integrates multiple, reusable modules that are trained specifically for their individual tasks (semantic parser, entity andrelationship linkers, and neuro-symbolic reasoner) and do not require end-to-end training data. NSQA achieves state-of-the-art performance on two prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD1.0). Furthermore, our analysis emphasizes that AMR is a powerful tool for KBQA systems.
Cite
@article{arxiv.2012.01707,
title = {Leveraging Abstract Meaning Representation for Knowledge Base Question Answering},
author = {Pavan Kapanipathi and Ibrahim Abdelaziz and Srinivas Ravishankar and Salim Roukos and Alexander Gray and Ramon Astudillo and Maria Chang and Cristina Cornelio and Saswati Dana and Achille Fokoue and Dinesh Garg and Alfio Gliozzo and Sairam Gurajada and Hima Karanam and Naweed Khan and Dinesh Khandelwal and Young-Suk Lee and Yunyao Li and Francois Luus and Ndivhuwo Makondo and Nandana Mihindukulasooriya and Tahira Naseem and Sumit Neelam and Lucian Popa and Revanth Reddy and Ryan Riegel and Gaetano Rossiello and Udit Sharma and G P Shrivatsa Bhargav and Mo Yu},
journal= {arXiv preprint arXiv:2012.01707},
year = {2021}
}
Comments
Accepted to Findings of ACL