情报杂志2023，Vol.42Issue(12)：153-158,167,7.DOI:10.3969/j.issn.1002-1965.2023.12.022
基于迁移学习与细粒度文本特征的未见关系链接研究
Research on Unseen Relation Linking Based on Transfer Learning and Fine-grained Features
摘要
Abstract
[Research purpose]In the era of explosive knowledge growth,knowledge graph question answering is facing the reality of in-formation demand and knowledge graph accelerated updates.Therefore,It is urgent to explore relation linking methods to maintain linking effectiveness and achieve accurate semantic matching between unseen relations and questions when relations are frequently updated.[Re-search method]To address the problems of inadequate model generalization and catastrophic forgetting,we adapt Adapter-Bert transfer learning framework.To address the problem of inadequate capture of discriminative semantic parts,we add entity feature and question transformation to model,and combine two different semantic representation methods which are dense vectors and abstract meaning formal-ized representation.[Research conclusion]The results show that the accuracy of our unseen relation linking method reached 98.80%,which is significantly higher than the Bert baseline model,and improves the effectiveness of unseen relation linking.关键词
自然语言处理/未见关系/迁移学习/细粒度文本特征/抽象意义表示Key words
natural language processing/unseen relation/transfer learning/fine-grained features/abstract meaning representation分类
信息技术与安全科学引用本文复制引用
徐红霞..基于迁移学习与细粒度文本特征的未见关系链接研究[J].情报杂志,2023,42(12):153-158,167,7.基金项目
北京市自然科学基金项目"计算档案学视角下城市历史遗迹孪生数据管护研究"(编号:9222015)的研究成果. （编号:9222015）
