Phrase Based and Neural Network Translation for Text Transliteration from Arabic to Indonesia

Alvian Burhanuddin (Universitas Islam Negeri Maulana Malik Ibrahim Malang)
Ahmad Latif Qosim (Universitas Islam Negeri Maulana Malik Ibrahim Malang)
Rizqi Amaliya (Universitas Islam Negeri Maulana Malik Ibrahim Malang)

MATICS : Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology)
Vol 14, No 1 (2022): MATICS

Abstract- Transliteration is one solution to overcome the inability to read and write Arabic in Indonesia. However, this transliteration has many different versions in reality. The many differences in transliteration versions make it difficult for people to understand and pronounce the Arabic sentence. So there needs to be an approach to overcome the problem of these differences. The data mining approach can be used as an option to reduce these differences. In this study, the researcher found that automatic transliteration based on the data mining model had a reasonably good BLEU value.