Dynamic Relevance Graph Network for Knowledge-Aware Question Answering

Chen Zheng, Parisa Kordjamshidi


Abstract
This work investigates the challenge of learning and reasoning for Commonsense Question Answering given an external source of knowledge in the form of a knowledge graph (KG). We propose a novel graph neural network architecture, called Dynamic Relevance Graph Network (DRGN). DRGN operates on a given KG subgraph based on the question and answers entities and uses the relevance scores between the nodes to establish new edges dynamically for learning node representations in the graph network. This explicit usage of relevance as graph edges has the following advantages, a) the model can exploit the existing relationships, re-scale the node weights, and influence the way the neighborhood nodes’ representations are aggregated in the KG subgraph, b) It potentially recovers the missing edges in KG that are needed for reasoning. Moreover, as a byproduct, our model improves handling the negative questions due to considering the relevance between the question node and the graph entities. Our proposed approach shows competitive performance on two QA benchmarks, CommonsenseQA and OpenbookQA, compared to the state-of-the-art published results.
Anthology ID:
2022.coling-1.116
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1357–1366
Language:
URL:
https://aclanthology.org/2022.coling-1.116
DOI:
Bibkey:
Cite (ACL):
Chen Zheng and Parisa Kordjamshidi. 2022. Dynamic Relevance Graph Network for Knowledge-Aware Question Answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1357–1366, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Dynamic Relevance Graph Network for Knowledge-Aware Question Answering (Zheng & Kordjamshidi, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.116.pdf
Code
 hlr/drgn
Data
CommonsenseQAConceptNetOpenBookQA