Dynamic Relevance Graph Network for Knowledge-Aware Question Answering
Chen
Zheng
author
Parisa
Kordjamshidi
author
2022-10
text
Proceedings of the 29th International Conference on Computational Linguistics
International Committee on Computational Linguistics
Gyeongju, Republic of Korea
conference publication
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.
zheng-kordjamshidi-2022-dynamic
https://aclanthology.org/2022.coling-1.116
2022-10
1357
1366