Knowledge-aware adaptive graph network for commonsense question answering

Commonsense Question Answering (CQA) aims to select the correct answers to common knowledge questions. Most existing approaches focus on integrating external knowledge graph (KG) representations with question context representations to facilitate reasoning. However, the approaches cannot effectively...

Full description

Saved in:
Bibliographic Details
Published in:Journal of intelligent information systems 2024-10, Vol.62 (5), p.1305-1324
Main Authors: Kang, Long, Li, Xiaoge, An, Xiaochun
Format: Article
Language:English
Subjects:
Ablation
Artificial Intelligence
Computer Science
Data Structures and Information Theory
Graph theory
Graphical representations
Information Storage and Retrieval
IT in Business
Knowledge
Knowledge representation
Natural Language Processing (NLP)
Nodes
Questions
Reasoning
Semantics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Commonsense Question Answering (CQA) aims to select the correct answers to common knowledge questions. Most existing approaches focus on integrating external knowledge graph (KG) representations with question context representations to facilitate reasoning. However, the approaches cannot effectively select the correct answer due to (i) the incomplete reasoning chains when using knowledge graphs as external knowledge, and (ii) the insufficient understanding of semantic information of the question during the reasoning process. Here we propose a novel model, KA-AGN. First, we utilize a joint representation of dependency parse trees and language models to describe QA pairs. Next, we introduce question semantic information as nodes into a knowledge subgraph and compute the correlations between nodes using adaptive graph networks. Finally, bidirectional attention and graph pruning are employed to update the question representation and the knowledge subgraph representation. To evaluate the performance of our method, we conducted experiments on two widely used benchmark datasets: CommonsenseQA and OpenBookQA. The ablation experiment results demonstrate the effectiveness of the adaptive graph network in enhancing reasoning chains, while showing the ability of the joint representation of dependency parse trees and language models to correctly understand question semantics. Our code is publicly available at https://github.com/agfsghfdhg/KAAGN-main .
ISSN:0925-9902
1573-7675
DOI:10.1007/s10844-024-00854-z