English Indonesia-Chan: OPUS-MT Powered Chatbot

Jerry Lasama, Sudianto Sudianto, Rafian Ramadhani, Muhammad David Hilmawan, Muhammad Yusril Aldean, Muhammad Adhan Hady Satria

Abstract


The COVID-19 pandemic has shown an increasing trend of digital platform users on social media such as Whatsapp, Facebook, Instagram, and Discord. The social media that is widely used to communicate massively is Discord. Discord already has 250 million registered active users from various countries worldwide. However, users from various countries create language differences when communicating. So we need a method for translating foreign languages, especially English to Indonesian, easily and quickly to make communication more understandable. This study aims to create a Discord chatbot that translates English sentences into Indonesian. The method built in the chatbot is designed using the MarianNMT model for language translation and the English corpus dataset from Open Parallel corPUS (OPUS). The model was trained using 15 epochs and obtained evaluation results with a loss of 0.0047.

Keywords


Chatbot; Discord; MarianNMT; NLP; Translate

Full Text:

PDF

References


N. K. Suni Astini, “Tantangan Dan Peluang Pemanfaatan Teknologi Informasi Dalam Pembelajaran Online Masa Covid-19,” Cetta J. Ilmu Pendidik., vol. 3, no. 2, pp. 241–255, 2020.

R. Komalasari, “Manfaat Teknologi Informasi Dan Komunikasi Di Masa Pandemi Covid 19,” Tematik, vol. 7, no. 1, pp. 38–50, 2020.

D. P. Covid-, “Pemanfaatan Media Komunikasi Whatsapp Untuk Mengoptimalisasi Kinerja Jurnalis,” vol. 16, no. 2, pp. 141–151, 2021.

J. Teknologi and I. Komunikasi, “Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) Vol. 8 No. 2 Desember 2021,” vol. 8, no. 2, pp. 160–175, 2021.

J. P. Raihan1) and M. , Yuliani Rachma Putri, S.Ip., “Pola Komunikasi Group Discord Pubg.Indo.Fun Melalui Aplikasi Discord,” vol. 5, no. 3, pp. 4161–4169, 2018.

M. R. Ridho, M. Muhaimin, and H. S. Harjono, “Pengaruh Aplikasi Discord Dalam Pembelajaran Daring Terhadap Hasil Belajar Pada Matakuliah Komputer,” J. Ilm. Bina Edukasi, vol. 14, no. 1, pp. 22–35, 2021.

S. Aditia, “Inovasi Pembelajaran Berbasis Aplikasi Mobile,” 2020.

Statista, “Aplikasi Berbasis Audio Discord Punya 300 Juta Pengguna.” https://databoks.katadata.co.id/datapublish/2021/02/24/aplikasi-berbasis-audio-discord-punya-300-juta-pengguna (accessed Jan. 12, 2022).

E. First, “Indeks Kecakapan Berbahasa Inggris di Asia Tenggara (2020),” 2020. Indeks Kecakapan Berbahasa Inggris (EPI) versi Education First (EF) di Asia Tenggara masih dipimpin Singapura pada 2020. Negeri tetangga tersebut berhasil mengantongi 611 poin dari 800 poin. Sehingga membawa Singapura di posisi 10 dunia dari 100 negara da (accessed Jan. 12, 2022).

English Firts, “EF English Proficiency Index 2021,” 2021. https://www.ef.com/wwen/epi/regions/asia/indonesia/ (accessed Jan. 12, 2022).

I. G. N. P. K. Gek Wulan Novi Utami, “Pemaknaan Verba Bahasa Inggris Dan Upaya Peningkatan Pengajaran Dan Pembelajaran Verba,” vol. 4, no. 1, pp. 77–82, 2018.

I. N. Norambuena and A. Bergel, “Building a bot for automatic expert retrieval on discord,” MaLTESQuE 2021 - Proc. 5th Int. Work. Mach. Learn. Tech. Softw. Qual. Evol. co-located with ESEC/FSE 2021, no. Dcc, pp. 25–30, 2021.

A. G. Jones and D. Wijaya, “Sentiment-based Candidate Selection for NMT,” Proc. Mach. Transl. Summit XVIII Res. Track, pp. 188–201, 2021.

R. A. Rahmanda, M. Adriani, and D. Tanaya, “Cross Language Information Retrieval Using Parallel Corpus with Bilingual Mapping Method,” Proc. 2019 Int. Conf. Asian Lang. Process. IALP 2019, pp. 222–227, 2019.

D. Puspitaningrum, “A Study of English-Indonesian Neural Machine Translation with Attention (Seq2Seq, ConvSeq2Seq, RNN, and MHA),” Conf. Sustain. Inf. Eng. Technol. 2021, pp. 271–280, 2021.

O. Zahour, E. H. Benlahmar, A. Eddaoui, H. Ouchra, and O. Hourrane, “A system for educational and vocational guidance in Morocco: Chatbot e-orientation,” Procedia Comput. Sci., vol. 175, pp. 554–559, 2020.

R. Darwis, H. Sujaini, and R. D. Nyoto, “Peningkatan Mesin Penerjemah Statistik dengan Menambah Kuantitas Korpus Monolingual (Studi Kasus : Bahasa Indonesia - Sunda),” J. Sist. dan Teknol. Inf., vol. 7, no. 1, p. 27, 2019.

J. Tiedemann, “Parallel data, tools and interfaces in OPUS,” Proc. 8th Int. Conf. Lang. Resour. Eval. Lr. 2012, pp. 2214–2218, 2012.

S. Sudianto, A. D. Sripamuji, I. R. Ramadhanti, R. R. Amalia, J. Saputra, and B. Prihatnowo, “Penerapan Algoritma Support Vector Machine dan Multi-Layer Perceptron pada Klasifikasi Topik Berita,” Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI, vol. 11, no. 2, pp. 84–91, 2022.

S. Sudianto, P. Wahyuningtias, H. W. Utami, U. A. Raihan, and H. N. Hanifah, “Comparison Of Random Forest And Support Vector Machine Methods On Twitter Sentiment Analysis ( Case Study : Internet Selebgram Rachel Vennya Escape From Quarantine ) Perbandingan Metode Random Forest Dan Support Vector Machine Pada Analisis Sentimen Twitt,” Jutif, vol. 3, no. 1, pp. 141–145, 2022.

W. Afandi, S. N. Saputro, A. M. Kusumaningrum, H. Ardiansyah, M. H. Kafabi, and S. Sudianto, “Klasifikasi Judul Berita Clickbait menggunakan RNN-LSTM,” Jurnal Pengembangan IT, vol. 7, no. 2, pp. 85–89, 2022.

S. Sudianto, J. A. Marseli, N. Nugroho, R. W. A. Rumpoko, and Z. Akhmad, “Comparison of Support Vector Machines and K-Nearest Neighbor Algorithm Analysis of Spam Comments on YouTube Covid Omicron,” JTI, vol. 15, no. 2, pp. 110–118, 2022.

S. Sudianto, “Analisis Kinerja Algoritma Machine Learning Untuk Klasifikasi Emosi,” vol. 4, no. 2, pp. 1027–1034, 2022.

S. Chandra Ayunda Apta, N. Trivetisia, N. A. Winanti, D. P. Martiyaningsih, T. W. Utami, and S. Sudianto, “Analisis Komparasi Algoritma Machine Learning untuk Sentiment Analysis (Studi Kasus: Komentar YouTube ‘Kekerasan Seksual’),” Jurnal Pengembangan IT, vol. 7, no. 2, pp. 80–84, 2022.

J. Tiedemann and S. Thottingal, “OPUS-MT: Building Open Translation Services for the World,” Proc. 22nd Annu. Conf. Eur. Assoc. Mach. Transl., pp. 479–480, 2020.




DOI: https://doi.org/10.32528/elkom.v6i1.18613

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Jurnal Teknik Elektro dan Komputasi (ELKOM)

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

View My Status                                                                       Indexing Service

                              

UNMUH

   Publisher :
   UNIVERSITAS MUHAMMADIYAH JEMBER
   Jl. Karimata No. 49 Jember 68121 East Java
   Website : www.unmuhjember.ac.id
   Email : kantorpusat@unmuhjember.ac.id

Editorial Address :
Electrical Engineering
Faculty of Engineering
UNIVERSITAS MUHAMMADIYAH JEMBER
Jl. Karimata No. 49 Jember 68121 East Java