###
计算机系统应用:2019,28(1):194-199
本文二维码信息
码上扫一扫!
基于GloVe模型的词向量改进方法
(北京工业大学 信息学部, 北京 100124)
Improved Word Representation Based on GloVe Model
(Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 172次   下载 91
投稿时间:2018-06-04    修订日期:2018-06-27
中文摘要: 使用词向量表示方法能够很好的捕捉词语的语法和语义信息,为了能够提高词向量语义信息表示的准确性,本文通过分析GloVe模型共现矩阵的特点,利用分布式假设,提出了一种基于GloVe词向量训练模型的改进方法.该方法主要通过对维基百科统计词频分析,总结出过滤共现矩阵中无关词和噪声词的一般规律,最后给出了词向量在词语类比数据集和词语相关性数据集的评估结果.实验表明,在相同的实验环境中,本文的方法能够有效的缩短词向量的训练时间,并且在词语语义类比实验中准确率得到提高.
中文关键词: 词向量  Word2Vec  GloVe  共现矩阵  无关词
Abstract:Word vector representation is a sound way to catch the grammatical and semantic information of words. In order to improve the accuracy of the semantic information of the word, this study proposes an improved training method model based on the GloVe by analyzing the characteristics of the co-occurrence matrix and using the distributed hypothesis. This method summarizes the general rules of irrelevant words and noise words in the co-occurrence matrix from analyzing the word frequency of Wikipedia statistics. Finally, we give the evaluation results of word vector in word analogy dataset and word correlation dataset. Experiments show that the method presented in this paper can effectively shorten the training time and the accuracy of the word semantic analogy experiment is improved in the same experimental environment.
文章编号:     中图分类号:    文献标志码:
基金项目:国家重点研发计划(2017YFC0803300);北京市教委项目(KM201810005023,KM201810005024,KZ201610005009);国家自然科学基金(61402449,61703013,91546111,91646201);北京市科技计划项目(Z161100001116072)
引用文本:
陈珍锐,丁治明.基于GloVe模型的词向量改进方法.计算机系统应用,2019,28(1):194-199
CHEN Zhen-Rui,DING Zhi-Ming.Improved Word Representation Based on GloVe Model.COMPUTER SYSTEMS APPLICATIONS,2019,28(1):194-199

用微信扫一扫

用微信扫一扫