TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs

Aditya Sharma, Apoorv Saxena, Chitrank Gupta, Mehran Kazemi, Partha Talukdar, Soumen Chakrabarti


Abstract
Recent years have witnessed interest in Temporal Question Answering over Knowledge Graphs (TKGQA), resulting in the development of multiple methods. However, these are highly engineered, thereby limiting their generalizability, and they do not automatically discover relevant parts of the KG during multi-hop reasoning. Relational graph convolutional networks (RGCN) provide an opportunity to address both of these challenges – we explore this direction in the paper. Specifically, we propose a novel, intuitive and interpretable scheme to modulate the messages passed through a KG edge during convolution based on the relevance of its associated period to the question. We also introduce a gating device to predict if the answer to a complex temporal question is likely to be a KG entity or time and use this prediction to guide our scoring mechanism. We evaluate the resulting system, which we call TwiRGCN, on a recent challenging dataset for multi-hop complex temporal QA called TimeQuestions. We show that TwiRGCN significantly outperforms state-of-the-art models on this dataset across diverse question types. Interestingly, TwiRGCN improves accuracy by 9–10 percentage points for the most difficult ordinal and implicit question types.
Anthology ID:
2023.eacl-main.150
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2049–2060
Language:
URL:
https://aclanthology.org/2023.eacl-main.150
DOI:
10.18653/v1/2023.eacl-main.150
Bibkey:
Cite (ACL):
Aditya Sharma, Apoorv Saxena, Chitrank Gupta, Mehran Kazemi, Partha Talukdar, and Soumen Chakrabarti. 2023. TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2049–2060, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs (Sharma et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.150.pdf
Software:
 2023.eacl-main.150.software.zip
Video:
 https://aclanthology.org/2023.eacl-main.150.mp4