基于图对比的上下位关系检测  

Hypernymy detection based on graph contrast

作　　者：张雅丽[1] 方全[2] 王允鑫 胡骏 钱胜胜 徐常胜[2] ZHANG Yali;FANG Quan;WANG Yunxin;Hu Jun;QIAN Shengsheng;XU Changsheng(Henan Institute of Advanced Technology,Zhengzhou University,Zhengzhou 450000,China;National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]郑州大学河南先进技术研究院,郑州450000 [2]中国科学院自动化研究所模式识别国家重点实验室,北京100190

出　　处：《北京航空航天大学学报》2022年第8期1480-1486,共7页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(62072456,62036012);之江实验室开放课题(2021KE0AB05)。

摘　　要：上下位关系是自然语言处理(NLP)下游任务的基础,因此上下位关系检测是自然语言处理领域备受关注的问题。针对现有词嵌入方法采用随机初始化词向量,不能很好地捕获上下位关系不对称和可传递的特性,且现有模型没有充分利用预测向量与真实投影之间关系的局限性,提出了一种基于图对比学习的上下位关系检测(HyperCL)方法。引入图对比学习进行数据增强,基于最大化局部和全局表示的互信息,学习具有鲁棒性的词特征表示。所提方法学习了将下位词的词向量投影到上位词和非上位词,同时能够更好地区分嵌入空间中的上位词和非上位词,从而提高了检测精度。在2个基准数据集上的实验结果表明,所提模型比现有方法在准确率上提升了0.03以上。Hypernymy is the foundation of many downstream tasks in natural language processing(NLP),so hypernymy detection has received considerable attention in the field of NLP.Adopting random initialization word vectors,existing word embedding methods cannot well capture the asymmetry and transferability of hypernymy,or make full use of the relationship between the prediction vector and the real projection.To address these problems,a novel method is proposed for detecting hypernymy based on graph contrastive learning(HyperCL).Firstly,HyperCL is introduced for data enhancement,and robust word feature representations are learned based on maximizing mutual information between local and global representations.Secondly,the proposed method learns how to project the hyponym vector to its hypernym and non-hypernym,and better distinguish the hypernym and non-hypernym in the embedded space,thus improving the detection accuracy.Experimental results on two benchmark datasets show that the proposed model increases the accuracy by more than 0.03,compared with the existing methods.

关 键 词：自然语言处理(NLP) 上下位关系检测 图对比学习 数据增强 词嵌入 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]