基于排序学习的构件检索方法的研究  

A component retrieval method based on learning to rank

作　　者：陈华烨 汪海涛[1] 姜瑛[1] 陈星[1] CHEN Hua-ye;WANG Hai-tao;JIANG Ying;CHEN Xing(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《计算机工程与科学》2021年第6期1006-1013,共8页Computer Engineering & Science

基　　金：国家自然科学基金(61462049)。

摘　　要：将排序学习的方法应用于构件检索的研究中,首先,采用刻面描述的方法对构件进行全面的描述,并通过word2vec模型和权重设定的方法对刻面描述的构件进行特征提取;然后,对构件特征进行潜在语义分析和余弦相似度计算,得到构件训练数据集;最后,通过使用构件训练数据集和构件数据集对经过改进的Plackett-Luce概率排序模型用最大似然估计方法训练模型参数,从而得到一种构件排序模型。将构件排序模型应用到构件检索中开发实现了一个构件检索方法,通过实验验证了此方法的有效性,其查全率、查准率和效率都优于传统的构件检索方法。This paper applies the method of learning to rank to the research of component retrieval.Firstly,the facet description method is used to describe the components comprehensively,and the features of the facet described components are extracted through the Word2vec model and the weight setting method.Secondly,the component semantics analysis and cosine similarity calculation are performed on the component feature description information to obtain the component training data set.Finally,the component training data set and the component data set are used to train the model parameters of the improved Plackett-Luce probabilistic ranking model through the maximum likelihood estimation method,so as to obtain a component ranking model.The component ranking model is applied to the component retrieval to realize a component retrieval method.Experiments show that the method has better effectiveness,recall,precision and efficiency are better than the traditional component retrieval methods.

关 键 词：排序学习 构件检索 潜在语义分析 最大似然估计 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]