A Two-Stage Approach towards Generalization in Knowledge Base Question Answering

Srinivas Ravishankar, Dung Thai, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Tahira Naseem, Pavan Kapanipathi, Gaetano Rossiello, Achille Fokoue


Abstract
Most existing approaches for Knowledge Base Question Answering (KBQA) focus on a specific underlying knowledge base either because of inherent assumptions in the approach, or because evaluating it on a different knowledge base requires non-trivial changes. However, many popular knowledge bases share similarities in their underlying schemas that can be leveraged to facilitate generalization across knowledge bases. To achieve this generalization, we introduce a KBQA framework based on a 2-stage architecture that explicitly separates semantic parsing from the knowledge base interaction, facilitating transfer learning across datasets and knowledge graphs. We show that pretraining on datasets with a different underlying knowledge base can nevertheless provide significant performance gains and reduce sample complexity. Our approach achieves comparable or state-of-the-art performance for LC-QuAD (DBpedia), WebQSP (Freebase), SimpleQuestions (Wikidata) and MetaQA (Wikimovies-KG).
Anthology ID:
2022.findings-emnlp.408
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5571–5580
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.408
DOI:
10.18653/v1/2022.findings-emnlp.408
Bibkey:
Cite (ACL):
Srinivas Ravishankar, Dung Thai, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Tahira Naseem, Pavan Kapanipathi, Gaetano Rossiello, and Achille Fokoue. 2022. A Two-Stage Approach towards Generalization in Knowledge Base Question Answering. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5571–5580, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
A Two-Stage Approach towards Generalization in Knowledge Base Question Answering (Ravishankar et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.408.pdf