{"title":"TSMiner: from TSBuilder to Ecosystem","authors":"V. Bakhtin, E. Isaeva, Andrey V. Tararkov","doi":"10.1109/ElConRus51938.2021.9396569","DOIUrl":null,"url":null,"abstract":"The paper reviews a project on the automation of term system construction. TSBuilder (Term System Builder) was developed in 2014 for supervised machine learning, namely 1-3 word terms identification in natural language texts and their categorization. TSGraph (Term System Graph) was developed in 2019 for visualization of terminologies’ overlappings.TSMiner is the integration of existing projects into an ecosystem allowing to move smoothly from search to storage and visualization of terminologies.We added the use of synonymic matching for single- and multiple-word terms at the morphemic level, which is beyond the scope of a traditional linguistic analysis. This allows us to replenish the database with new words close in meaning to the existing ones but having dropped out of our radar for not being cognit to the ones included into the database. Algorithms for translating natural language words into a vector form were used to estimate the degree of synonymy.","PeriodicalId":447345,"journal":{"name":"2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ElConRus51938.2021.9396569","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The paper reviews a project on the automation of term system construction. TSBuilder (Term System Builder) was developed in 2014 for supervised machine learning, namely 1-3 word terms identification in natural language texts and their categorization. TSGraph (Term System Graph) was developed in 2019 for visualization of terminologies’ overlappings.TSMiner is the integration of existing projects into an ecosystem allowing to move smoothly from search to storage and visualization of terminologies.We added the use of synonymic matching for single- and multiple-word terms at the morphemic level, which is beyond the scope of a traditional linguistic analysis. This allows us to replenish the database with new words close in meaning to the existing ones but having dropped out of our radar for not being cognit to the ones included into the database. Algorithms for translating natural language words into a vector form were used to estimate the degree of synonymy.
本文综述了一个学期系统建设自动化项目。TSBuilder (Term System Builder)于2014年开发,用于监督机器学习,即在自然语言文本中识别1-3个单词的术语并进行分类。TSGraph(术语系统图)于2019年开发,用于可视化术语重叠。TSMiner将现有项目集成到一个生态系统中,允许从搜索到存储和可视化术语的平滑移动。我们在语素级别为单词和多词术语添加了同义词匹配的使用,这超出了传统语言分析的范围。这使我们能够用与现有单词含义相近的新词来补充数据库,但由于没有认识到数据库中包含的单词而被排除在我们的雷达之外。将自然语言单词翻译成向量形式的算法用于估计同义词的程度。