Knowledge Base Question Answering through Recursive Hypergraphs
Naganand Yadati, Dayanidhi R S, Vaishnavi S, Indira K M, Srinidhi G
Abstract
Knowledge Base Question Answering (KBQA) is the problem of predicting an answer for a factoid question over a given knowledge base (KB). Answering questions typically requires reasoning over multiple links in the given KB. Humans tend to answer questions by grouping different objects to perform reasoning over acquired knowledge. Hypergraphs provide a natural tool to model group relationships. In this work, inspired by typical human intelligence, we propose a new method for KBQA based on hypergraphs. Existing methods for KBQA, though effective, do not explicitly incorporate the recursive relational group structure in the given KB. Our method, which we name RecHyperNet (Recursive Hypergraph Network), exploits a new way of modelling KBs through recursive hypergraphs to organise such group relationships in KBs. Experiments on multiple KBQA benchmarks demonstrate the effectiveness of the proposed RecHyperNet. We have released the code.- Anthology ID:
- 2021.eacl-main.35
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 448–454
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.35
- DOI:
- 10.18653/v1/2021.eacl-main.35
- Cite (ACL):
- Naganand Yadati, Dayanidhi R S, Vaishnavi S, Indira K M, and Srinidhi G. 2021. Knowledge Base Question Answering through Recursive Hypergraphs. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 448–454, Online. Association for Computational Linguistics.
- Cite (Informal):
- Knowledge Base Question Answering through Recursive Hypergraphs (Yadati et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.eacl-main.35.pdf
- Data
- MetaQA, WebQuestionsSP