基于数学表达式和文档关键词的英文文献检索模型设计  

Design of English Document Retrieval Model Based on Mathematical Expressions and Document Keywords

作　　者：张冠萍[1] ZHANG Guan-ping(Xi'an Siyuan University,Xi'an 710038 China)

机构地区：[1]西安思源学院,陕西西安710038

出　　处：《自动化技术与应用》2024年第12期107-109,129,共4页Techniques of Automation and Applications

基　　金：陕西省教育科学规划课题(SGH17H448)。

摘　　要：为实现针对英文学术文献的准确检索,提出一套基于数学表达式和文档关键词的英文文献检索模型。通过FDS算法对数学表达式进行结构化描述,扩大英文文献的检索范围,同时通过基于Word2Vec的词嵌入模型对英文单词进行向量化表示,采用余弦定理来计算查询关键词向量与文档单词向量之间的相似度,根据相似度的高低来对单词进行排序,进而输出查询结果。最后通过NTCIR语料库对英文文献检索模型的有效性加以验证,根据实验结果可知,该模型在查准率和查全率两方面均达到了较为理想的效果,且显著优于常规SearchOnMath模型,具有一定的应用价值。In order to realize the accurate retrieval of English academic literature,this study proposes a set of English literature retrieval model based on mathematical expressions and document keywords.The FDS algorithm is used to describe the mathematical expression structurally and expand the search scope of English documents.At the same time,the word embedding model based on word2vec is used to vectorize the English words,and the cosine theorem is used to calculate the similarity between the query keyword vector and the document word vector.The words are sorted according to the similarity,and then the query results are output.Finally,the effectiveness of the English literature retrieval model is verified by the ntcir corpus.According to the experimental results,it can be seen that the model has achieved ideal results in both precision and recall,and is significantly better than the conventional searchonmath model.It has certain application value.

关 键 词：模型 数学表达式 运算符信息 文档关键词 文献检索 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.3[自动化与计算机技术—控制科学与工程]