Retrieval-Augmented Knowledge Graph Reasoning for Commonsense Question Answering
Mathematics · 25.07.2023 · 11 (15) · 3269
DOI: 10.3390/math11153269 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 25.07.2023. Verfasst von Yuchen Sha und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Open Research Project of Zhejiang Lab.
Abstract (Originalsprache)
Existing knowledge graph (KG) models for commonsense question answering present two challenges: (i) existing methods retrieve entities related to questions from the knowledge graph, which may extract noise and irrelevant nodes, and (ii) there is a lack of interaction representation between questions and graph entities. However, current methods mainly focus on retrieving relevant entities with some noisy and irrelevant nodes. In this paper, we propose a novel retrieval-augmented knowledge graph (RAKG) model, which solves the above issues using two key innovations. First, we leverage the density matrix to make the model reason along the corrected knowledge path and extract an enhanced subgraph of the knowledge graph. Second, we fuse representations of questions and graph entities through a bidirectional attention strategy, in which two representations fuse and update using a graph convolutional network (GCN). To evaluate the performance of our method, we conducted experiments on two widely used benchmark datasets: CommonsenseQA and OpenBookQA. The case study gives insight into the finding that the augmented subgraph provides reasoning along the corrected knowledge path for question answering.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Open Research Project of Zhejiang Lab
- Postgraduate Research & Practice Innovation Program of the Jiangsu Province
Zitieren
APA
Sha, Y., Feng, Y., He, M., Liu, S., & Ji, Y. (2023). Retrieval-Augmented Knowledge Graph Reasoning for Commonsense Question Answering. Mathematics, 11(15), 3269. https://doi.org/10.3390/math11153269
Vancouver
Sha Y, Feng Y, He M, Liu S, Ji Y. Retrieval-Augmented Knowledge Graph Reasoning for Commonsense Question Answering. Mathematics. 2023;11(15):3269. doi:10.3390/math11153269
BibTeX
@article{Sha2023,
author = {Sha, Yuchen and Feng, Yujian and He, Miao and Liu, Shangdong and Ji, Yimu},
title = {Retrieval-Augmented Knowledge Graph Reasoning for Commonsense Question Answering},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {15},
pages = {3269},
doi = {10.3390/math11153269}
}
EUVIMED