Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Computatio Journal o...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Computatio Journal of Computer Science and Information Systems
Article . 2019 . Peer-reviewed
License: CC BY NC SA
Data sources: Crossref
versions View all 1 versions
addClaim

SISTEM PENGOREKSIAN EJAAN TEKS BAHASA INDONESIA DENGAN DAMERAU LEVENSHTEIN DISTANCE DAN RECURRENT NEURA L NETWORK

Authors: Fendy Augusfian; Viny Christanti Mawardi; Janson Hendryli; Dali Santun Naga;

SISTEM PENGOREKSIAN EJAAN TEKS BAHASA INDONESIA DENGAN DAMERAU LEVENSHTEIN DISTANCE DAN RECURRENT NEURA L NETWORK

Abstract

This research was intended to create Indonesian Text Spelling Correction system with the capability to handle and make correction to both kind of spelling errors, non-word and real-word errors. Existing spelling correction system was analyzed and made some adjustment and modifications to boost its accuracy. The proposed spelling correction system is built with Damerau-Levenshtein Distance that used in existing spelling correction system along with the adjustment and modifications. The result that achieved by the system that uses by existing spelling correction with the word level accuracy of 40.6% and an average processing speed of 18.4 ms per sentence while the result that achieved by the system that uses Damerau-Levenshtein Distance and Recurrent Neural Network with the word level accuracy of 21.3% and an average processing speed of 29.21 ms per sentence. The result of retest text that achieved by the system that uses Damerau-Levenshtein Distance and Recurrent Neural Network with the word level accuracy of 74%. Tujuan dari penelitian ini adalah untuk membuat sistem pengoreksian ejaan teks Bahasa Indonesia, yang memiliki kemampuan untuk menangani dan memperbaiki kesalahan ejaan, baik kesalahan kata tidak sah maupun kesalahan kata sah. Sistem koreksi ejaan yang sudah ada dianalisis kembali dan dilakukan beberapa penyesuaian dan koreksi untuk meningkatkan akurasi. Sistem koreksi ejaan yang diusulkan dibuat dengan metode Damerau-Levenshtein, yang digunakan dengan penyesuaian dan koreksi dalam sistem koreksi ejaan yang sudah ada. Pencapaian yang dicapai oleh sistem koreksi ejaan yang sudah ada menghasilkan akurasi kata sebesar 40,6% dan kecepatan pemrosesan rata-rata 18,4 milidetik per kalimat dibandingkan hasil yang dicapai oleh sistem yang menggunakan Damerau-Levenshtein Distance dan Recurrent Neural Network Akurasi menghasilkan akurasi kata sebesar 21,3% dan kecepatan pemrosesan rata-rata adalah 29,21 milidetik per kalimat. Hasil pengujian ulang teks yang dicapai oleh sistem menggunakan Damerau-Levenshtein Distance dan Recurrent Neural Network menunjukkan akurasi kata sebesar dari 74%. 

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
gold