{"title":"Fast and Accurate Spelling Correction Using Trie and Damerau-levenshtein Distance Bigram","authors":"Viny Christanti M., Rudy Rudy, D. S. Naga","doi":"10.12928/telkomnika.v16i2.6890","DOIUrl":null,"url":null,"abstract":"This research was intended to create a fast and accurate spelling correction system with the ability to handle both kind of spelling errors, non-word and real word errors. Existing spelling correction system was analyzed and was then applied some modifications to improve its accuracy and speed. The proposed spelling correction system is then built based on the method and intuition used by existing system along with the modifications made in previous step. The result is a various spelling correction system using different methods. Best result is achieved by the system that uses bigram with Trie and Damerau-Levenshtein distance with the word level accuracy of 84.62% and an average processing speed of 18.89 ms per sentence.","PeriodicalId":414053,"journal":{"name":"TELKOMNIKA : Indonesian Journal of Electrical Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"TELKOMNIKA : Indonesian Journal of Electrical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.12928/telkomnika.v16i2.6890","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 15
Abstract
This research was intended to create a fast and accurate spelling correction system with the ability to handle both kind of spelling errors, non-word and real word errors. Existing spelling correction system was analyzed and was then applied some modifications to improve its accuracy and speed. The proposed spelling correction system is then built based on the method and intuition used by existing system along with the modifications made in previous step. The result is a various spelling correction system using different methods. Best result is achieved by the system that uses bigram with Trie and Damerau-Levenshtein distance with the word level accuracy of 84.62% and an average processing speed of 18.89 ms per sentence.
本研究旨在创建一个快速准确的拼写纠正系统,能够处理各种拼写错误,非单词和真正的单词错误。对现有的拼写纠错系统进行了分析,并对其进行了改进,以提高拼写纠错系统的准确性和速度。然后,根据现有系统使用的方法和直觉,以及上一步所做的修改,构建拟议的拼写纠正系统。其结果是使用不同方法的各种拼写纠正系统。使用Trie距离和Damerau-Levenshtein距离的双字库的准确率为84.62%,平均处理速度为18.89 ms /句,取得了最好的结果。