基于本体语义网络的语言理解模型  

Language Understanding Model Based on Ontological Semantics Network

作　　者：王飞 易绵竹 谭新 WANG Fei1, YI Mian -zhu1,TAN Xin2(1.Information Engineering University Luoyang Campus,Luoyang,Henan 471003,China;2.91709 Troops, Hunchun ,Jilin 133300, Chin)

机构地区：[1]信息工程大学洛阳校区 [2]91709部队

出　　处：《计算机科学》2018年第B06期101-105,共5页Computer Science

基　　金：国防科技创新特区项目:面向开放数据的大规模知识图谱构建及其应用(17-H863-01-ZT-005-008-03);国家自然科学基金项目:多语言言语数据获取;标注与分析研究(11590771)资助

摘　　要：传统的知识表示存在涵盖知识面不够和语义形式化描述不够全面的问题,导致计算机理解自然语言不够准确。受大脑神经元工作原理的启发,从语义剖析的角度出发,基于本体语义,在概念和词汇两个层次构建了本体语义网,使其具有神经网络的特性,既能准确理解文本语义,刻画词在不同领域内的不同含义,又涵盖了文本生成过程中的语义组合特点。为使模型进一步形式化,采用矩阵的方式表示,并用奇异值分解来降低矩阵规模复杂度,以便于描述词汇与概念之间的关系。The traditional knowledge representation has limited scope of knowledge and incomprehensive formal semantics description,thereby causing the computer＇s accurate portrayal of natural language.This paper proposed ontological semantics network on the levels of concept and lexicalfor semantic analysis.Its brain-like neural language network drawing from the inspiration of human brain neural cell＇s work principle,could both accurately portray different meanings of a word in different domains,understand the text meaning and cover the elements and characteristics in the process of words＇ s generating into sentences.Matrix is employed to further formalize the model,with singular value decomposition to reduce the scale complexity,which makes it more convenient to describe the relationship between lexical semantics.

关 键 词：概念 词汇 神经网络 本体语义 矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]