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

Ibrahim Abdelaziz, Srinivas Ravishankar, Pavan Kapanipathi, Salim Roukos, Alexander G. Gray

AAAI 2021 pp. 15985-15987

doi:10.1609/AAAI.V35I18.17988 /aaai/2021/abdelaziz2021aaai-semantic/

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.

PDF AAAI Semantic Scholar

Cite

Text

Abdelaziz et al. "A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17988

Markdown

[Abdelaziz et al. "A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/abdelaziz2021aaai-semantic/) doi:10.1609/AAAI.V35I18.17988

BibTeX

@inproceedings{abdelaziz2021aaai-semantic,
  title     = {{A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering}},
  author    = {Abdelaziz, Ibrahim and Ravishankar, Srinivas and Kapanipathi, Pavan and Roukos, Salim and Gray, Alexander G.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15985-15987},
  doi       = {10.1609/AAAI.V35I18.17988},
  url       = {https://mlanthology.org/aaai/2021/abdelaziz2021aaai-semantic/}
}