计算机工程与应用2025，Vol.61Issue(22)：123-136,14.DOI:10.3778/j.issn.1002-8331.2407-0421
MKML:用于零样本常识问答的多知识元学习算法
MKML:Multi-Knowledge Meta-Learning Algorithm for Zero-Shot Commonsense Question Answering
摘要
Abstract
Zero-shot commonsense question answering requires the model to answer unseen questions.Currently,most researchers inject knowledge graphs as commonsense knowledge.But when there is little overlap between the knowledge graph and the target dataset in terms of domains,increasing either the types of knowledge graphs or the number of triples within the graph cannot effectively enhance the question answering ability of the model on the target dataset.To address these limitations,this paper proposes a method called multi-knowledge meta-learning(MKML)for zero-shot common-sense question answering.This method trains different KG-Adapters to inject multiple knowledge graphs into the pre-trained model separately and merges the knowledge from these adapters by constructing a Meta-MoE module.At the same time,in order to enhance the ability of the model to answer unknown target domain questions based on its own knowledge,MKML updates the parameters of Meta-MoE through the construction of a multi-source meta-learning method.This helps the model acquire shared knowledge structure distribution information and enables it to identify unknown domain knowledge distributions based on the question prompts,thus quickly adapting to the target dataset.Experimental results on multiple commonsense question answering datasets demonstrate that compared to eight existing baseline methods,MKML exhibits higher accuracy in zero-shot commonsense question answering.关键词
零样本常识问答/知识图谱/元学习Key words
zero-shot commonsense question answering/knowledge graph/meta-learning分类
计算机与自动化引用本文复制引用
杨浩杰,鲁强..MKML:用于零样本常识问答的多知识元学习算法[J].计算机工程与应用,2025,61(22):123-136,14.基金项目
国家重点研发计划(2019YFC0312003). （2019YFC0312003）
