N. Kumar, M. Nagalakshmi, Tanya Sharma, S. Ambati, Vibha Satyanarayana
{"title":"Natural Language Interface to Linux Shell – Report","authors":"N. Kumar, M. Nagalakshmi, Tanya Sharma, S. Ambati, Vibha Satyanarayana","doi":"10.1109/ICCCT2.2019.8824800","DOIUrl":null,"url":null,"abstract":"Many a time, a user might not remember the exact Linux commands to apply while using the Linux shell. The programmer ends up searching for the correct solution. Having a natural language interface (like English) to a shell would help programmers’ in performing their desired tasks without having to think much about the particular command or option that needs to be used. We present a tool that can convert natural language into executable Linux commands. This paper covers the related work done in this field and our approach to solving this problem. Research in this field is fairly new and there are two tools in this domain, Tellina[1] and Betty. Tellina is a powerful tool which covers file operations with high complexity. Apart from file utilities, our tool also covers a wider scope of commands including awk and sed. A novel approach is used to find the structure of the command. This paper includes the comparisons between Neural Machine Translation (NMT), Statistical Machine Translation(SMT), similarity models and machine learning models.","PeriodicalId":445544,"journal":{"name":"2019 3rd International Conference on Computing and Communications Technologies (ICCCT)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 3rd International Conference on Computing and Communications Technologies (ICCCT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCCT2.2019.8824800","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
Many a time, a user might not remember the exact Linux commands to apply while using the Linux shell. The programmer ends up searching for the correct solution. Having a natural language interface (like English) to a shell would help programmers’ in performing their desired tasks without having to think much about the particular command or option that needs to be used. We present a tool that can convert natural language into executable Linux commands. This paper covers the related work done in this field and our approach to solving this problem. Research in this field is fairly new and there are two tools in this domain, Tellina[1] and Betty. Tellina is a powerful tool which covers file operations with high complexity. Apart from file utilities, our tool also covers a wider scope of commands including awk and sed. A novel approach is used to find the structure of the command. This paper includes the comparisons between Neural Machine Translation (NMT), Statistical Machine Translation(SMT), similarity models and machine learning models.