计算机与数字工程2024，Vol.52Issue(4)：1115-1118,1148,5.DOI:10.3969/j.issn.1672-9722.2024.04.027
基于知识图谱增强的自然语言推理方法研究
Research on Natural Language Interface Method Based on Knowledge Graph Enhancement
摘要
Abstract
Natural language inference(NLI)is an important task in natural language processing.It aims to identify the logical relationship that exists between two sentences.Most existing methods use the semantic knowledge obtained from the training corpus for reasoning.But it ignores the use and introduction of background knowledge.In this work,to solve this problem,a new NLI(KG-NET)model is proposed based on knowledge graph enhancement,so as to introduce the enhancement of related domain knowledge in the NLI task.The KGNET model is composed of three components,which are a semantic relationship representation module,a knowledge relationship representation module and a label prediction module.The experiments of the model on two benchmark datas-ets(SNLI and MultiNLI)verify the effectiveness of the model.关键词
自然语言推理/知识图谱/图神经网络/外部知识Key words
natural language interface/knowledge graph/graph neural network/external knowledge分类
信息技术与安全科学引用本文复制引用
朱彦,戚瑶瑶,凌骏,陶思雨..基于知识图谱增强的自然语言推理方法研究[J].计算机与数字工程,2024,52(4):1115-1118,1148,5.基金项目
国家自然科学基金项目(编号:61773167) （编号:61773167）
上海市科委项目(编号:19511120200)资助. （编号:19511120200）
