基于数据增强的地质文本主题模型  

Geological Text Topic Model Based on Data Augmentation

作　　者：张竞元 刘刚[1,2] 曾粤 周大双 陈麒玉 ZHANG Jing-Yuan;LIU Gang;ZENG Yue;ZHOU Da-Shuang;CHEN Qi-Yu(School of Computer Science,China University of Geosciences(Wuhan),Wuhan 430074,China;Hubei Key Laboratory of Intelligent Geo-Information Processing,Wuhan 430074,China)

机构地区：[1]中国地质大学(武汉)计算机学院,武汉430074 [2]智能地学信息处理湖北省重点实验室,武汉430074

出　　处：《计算机系统应用》2022年第7期290-297,共8页Computer Systems & Applications

基　　金：国家自然科学基金联合重点项目(U1711267);水利部协作项目(2019306340);中国地质大学(武汉)国家级创新训练计划(201810491232)。

摘　　要：直接利用主题模型对地质文本进行聚类时会出现主题准确性低、主题关键词连续性差等问题,本文采取了相关改进方法.首先在分词阶段采用基于词频统计的重复词串提取算法,保留地质专业名词以准确提取文本主题,同时减少冗余词串数量节约内存花销,提升保留词的提取效率.另外,使用基于TF-IDF和词向量的文本数据增强算法,对原始分词语料进行处理以强化文本主题特征.之后该算法与主题模型相结合在处理后的语料上提取语料主题.由于模型的先验信息得到增强,故性能得以提高.实验结果表明本文算法与LDA模型相结合的方法表现较好,在相关指标及输出结果上均优于其他方法.Problems such as low topic accuracy and poor continuity of topic keywords occur when geological texts are directly clustered by topic models.This study adopts relevant improvement methods.In the word segmentation stage,the repeated word string extraction algorithm based on word frequency statistics is adopted.Geological terms are retained to accurately extract text topics,and redundant word strings are reduced to save memory costs.In this way,the efficiency of retained word extraction is improved.In addition,a text data augmentation algorithm based on term frequency-inverse document frequency(TF-IDF)and word vector is used to process the original word segmentation corpus and thereby strengthen the text topic features.Then,the algorithm is combined with the topic model to extract the corpus topics on the processed corpus.The performance of the model is improved due to its enhanced prior information.The experimental results show that the method combining the proposed algorithm with the latent Dirichlet allocation(LDA)model performs well,superior to other methods in all the related indexes and output results.

关 键 词：地质文本 主题模型 数据增强 词向量 TF-IDF 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]