PENGEMBANGAN SISTEM AI PARAFRASE BAHASA INFORMAL KE FORMAL MENGGUNAKAN SENTENCE-BERT SIMILARITY DAN GEMINI API
DOI:
https://doi.org/10.54840/jcstech.v6i2.623Keywords:
Artificial Intelligence, Natural Language Processing, Sentence-BERT Similarity, Style transfer, Gemini APIAbstract
The use of informal language in digital communication often poses difficulties when users need to communicate formally, particularly in academic and professional contexts. This research aims to develop a system for paraphrasing informal Indonesian into formal Indonesian using the Retrieval-Augmented Style transfer (RAST) approach, which combines Sentence-BERT Similarity and the Gemini API. Sentence-BERT Similarity is used to search for example sentences with similar meanings from the dataset, whilst the Gemini API is used to generate formal paraphrases through a style transfer process. The dataset used consists of 1,110 pairs of informal and formal sentences divided into four communication contexts: lecturers, university administration, LinkedIn, and job application emails. The implementation results show that the system is capable of generating formal sentences that are more polite, clear, and appropriate to the communication context selected by the user. Manual evaluation results indicate that the system achieved an overall average score of 4.54, categorised as ‘very good’. The combination of Sentence-BERT Similarity and the Gemini API is effective in facilitating the transformation of informal language into formal language whilst preserving the core meaning of the message. This research is expected to contribute to the development of Indonesian Natural Language Processing applications, particularly in the fields of semantic Similarity and style transfer.
References
Budi, I. S., Putrayasa, I. B., Wisudariani, N., & Sudiana, I. N. (2024). PERAN DAN TANTANGAN PENGGUNAAN ARTIFICIAL INTELLIGENCE DALAM INOVASI PENGEMBANGAN KURIKULUM PEMBELAJARAN BAHASA INDONESIA MASA DEPAN. LEARNING : Jurnal Inovasi Penelitian Pendidikan dan Pembelajaran, 4(4), 1188–1194. https://doi.org/10.51878/learning.v4i4.3767
Bujnowski, P., Ryzhova, K., Choi, H., Witkowska, K., Piersa, J., Krumholc, T., & Beksa, K. (2020). An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation. Proceedings of the 28th International Conference on Computational Linguistics: Industry Track, 50–63. https://doi.org/10.18653/v1/2020.coling-industry.6
De Rivero, M., Tirado, C., & Ugarte, W. (2023). Formalstyler: GPT-Based Model for Formal Style Transfer with Meaning Preservation. SN Computer Science, 4(6), 739. https://doi.org/10.1007/s42979-023-02110-7
Eleison, K. C., Hutahaean, S. U. I., Tampubolon, S. C., Panggabean, T. M., & Fitriyaningsih, I. (2022). An empirical evaluation of phrase-based statistical machine translation for Indonesia slang-word translator. Indonesian Journal of Electrical Engineering and Computer Science, 25(3), 1803. https://doi.org/10.11591/ijeecs.v25.i3.pp1803-1813
Febriyanti, B. D., & Pitasari, M. A. R. (2023). ETIKA MAHASISWA DALAM MENGHUBUNGI DOSEN. FAJAR Jurnal Pendidikan Islam, 2(2), 186–197. https://doi.org/10.56013/fj.v2i2.1721
Holis, R. M., Utomo, P. E. P., & Hutabarat, B. F. (2025). Semantic FAQ Chatbot Using SBERT (Sentence-BERT) and Cosine Similarity for Academic Services. Brilliance: Research of Artificial Intelligence, 5(2), 915–922. https://doi.org/10.47709/brilliance.v5i2.7027
Khairul, M. F. R., & Perdana, R. S. (2024). Arsitektur Sistem Percakapan Otomatis Berbahasa Indonesia dengan Normalisasi Bahasa Informal Menjadi Baku. Jurnal Teknologi Informasi dan Ilmu Komputer, 11(5), 1009–1016. https://doi.org/10.25126/jtiik.1077984
Prawiro, I. Y., Yuliasri, I., Pratama, H., & Yuliati, Y. (2025). Integrating AI and Technology in Project-Based Learning for Academic Writing: Student Teachers’ Experiences from Indonesia. Educational Process International Journal, 19(1). https://doi.org/10.22521/edupij.2025.19.580
Syahnaz, M., & Fithriani, R. (2023). Utilizing Artificial Intelligence-based Paraphrasing Tool in EFL Writing Class: A Focus on Indonesian University Students’ Perceptions. Scope : Journal of English Language Teaching, 7(2), 210. https://doi.org/10.30998/scope.v7i2.14882
Wang, Y., Wu, Y., Mou, L., Li, Z., & Chao, W. (2020). Formality Style Transfer with Shared Latent Space. Proceedings of the 28th International Conference on Computational Linguistics, 2236–2249. https://doi.org/10.18653/v1/2020.coling-main.203
Wibowo, H. A., Prawiro, T. A., Ihsan, M., Aji, A. F., Prasojo, R. E., Mahendra, R., & Fitriany, S. (2020). Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation. 2020 International Conference on Asian Language Processing (IALP), 310–315. https://doi.org/10.1109/IALP51396.2020.9310459
Yao, Z., & Yu, H. (2021). Improving Formality Style Transfer with Context-Aware Rule Injection. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 1561–1570. https://doi.org/10.18653/v1/2021.acl-long.124
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Computer Science and Technology (JCS-TECH)

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