Method for the extraction of Russian-language multicomponent terms from scientific and technical texts

IF 0.4 Q4 MATHEMATICS, APPLIED
I. Butenko, A. Sapozhkov, Y. Stroganov
{"title":"Method for the extraction of Russian-language multicomponent terms from scientific and technical texts","authors":"I. Butenko, A. Sapozhkov, Y. Stroganov","doi":"10.37791/2687-0649-2021-16-6-21-27","DOIUrl":null,"url":null,"abstract":"The article presents a method for extracting Russian-language multicomponent terms from scientific and technical texts based on structural models of terminological collocations. The existing approaches to term extraction on the basis of the method of stable word combination extraction, statistical and hybrid methods are described, and the linguistic aspects of terminology, not covered by the listed methods, are noted. The lexical composition of scientific and technical texts is characterized, the classification of special vocabulary in scientific and technical texts is given. The structural features of terminological vocabulary have been studied. The most productive models of multi-component terminological word combinations in Russian are presented. A method for extracting Russian-language multicomponent terms from scientific and technical texts is offered, and its stages are described. It is shown that the first stage involves morphological and syntactic analysis of the text by attributing to each word its grammatical characteristics. Then there is the exclusion of parts of speech, which can not be part of the Russian multisyllabic terms, as well as stop-words, which together with the term form free word combinations. The resulting word chains are further correlated with the templates of terminological word combinations available in the database of structural models of terms, as well as the terminological dictionary for the presence of the studied candidate term. The necessity of involving a terminologist to resolve ambiguous cases is substantiated. Each step of the method for extracting Russian-language multicomponent terms in scientific and technical texts is illustrated by examples. Further research perspectives are listed, and the necessity of complicating the methods of text extraction, by further classification of terminological vocabulary according to formal and semantic structures, types of anthropomorphic terms, nomenclatural names, normativity/non-normativity of terminological units is substantiated.","PeriodicalId":44195,"journal":{"name":"Journal of Applied Mathematics & Informatics","volume":"11 1","pages":""},"PeriodicalIF":0.4000,"publicationDate":"2021-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Applied Mathematics & Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37791/2687-0649-2021-16-6-21-27","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATHEMATICS, APPLIED","Score":null,"Total":0}
引用次数: 0

Abstract

The article presents a method for extracting Russian-language multicomponent terms from scientific and technical texts based on structural models of terminological collocations. The existing approaches to term extraction on the basis of the method of stable word combination extraction, statistical and hybrid methods are described, and the linguistic aspects of terminology, not covered by the listed methods, are noted. The lexical composition of scientific and technical texts is characterized, the classification of special vocabulary in scientific and technical texts is given. The structural features of terminological vocabulary have been studied. The most productive models of multi-component terminological word combinations in Russian are presented. A method for extracting Russian-language multicomponent terms from scientific and technical texts is offered, and its stages are described. It is shown that the first stage involves morphological and syntactic analysis of the text by attributing to each word its grammatical characteristics. Then there is the exclusion of parts of speech, which can not be part of the Russian multisyllabic terms, as well as stop-words, which together with the term form free word combinations. The resulting word chains are further correlated with the templates of terminological word combinations available in the database of structural models of terms, as well as the terminological dictionary for the presence of the studied candidate term. The necessity of involving a terminologist to resolve ambiguous cases is substantiated. Each step of the method for extracting Russian-language multicomponent terms in scientific and technical texts is illustrated by examples. Further research perspectives are listed, and the necessity of complicating the methods of text extraction, by further classification of terminological vocabulary according to formal and semantic structures, types of anthropomorphic terms, nomenclatural names, normativity/non-normativity of terminological units is substantiated.
从科技文本中提取俄语多成分术语的方法
提出了一种基于术语搭配结构模型的俄语科技语篇多成分术语提取方法。介绍了基于稳定词组合提取方法、统计方法和混合方法的现有术语提取方法,并指出了所列方法未涵盖的术语语言学方面的问题。对科技语篇的词汇构成进行了表征,并对科技语篇中的特殊词汇进行了分类。对术语词汇的结构特征进行了研究。提出了俄语多成分术语词组合的最高产模型。提出了一种从俄语科技文本中提取多成分术语的方法,并描述了该方法的各个阶段。研究表明,第一阶段包括对文本进行形态和句法分析,赋予每个单词语法特征。然后是排除词性,这些词性不能成为俄语多音节术语的一部分,以及停止词,它们与术语一起形成自由词组合。生成的词链进一步与术语结构模型数据库中可用的术语词组合模板相关联,并与所研究的候选术语存在的术语词典相关联。涉及术语专家解决模棱两可的情况的必要性得到证实。用实例说明了俄语科技文本中多成分术语提取方法的各个步骤。提出了进一步的研究方向,并指出有必要根据形式和语义结构、拟人术语类型、命名名称、术语单位的规范性/非规范性等因素对术语词汇进行进一步分类,从而使文本提取方法复杂化。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
0.70
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信