CD Skripsi

Mesin Penerjemah Bahasa Aceh – Bahasa Indonesia Dan Sebaliknya Menggunakan Transfer Learning No Language Left Behind

---

ABSTRACT
Regional languages in Indonesia are very diverse, but are currently experiencing a decline in native speakers and are threatened with extinction, including in Aceh Province, Lhokseumawe City. This study aims to develop a machine translation model for Acehnese-Indonesian and vice versa by producing the best accuracy. The method used is Transfer Learning with the No Language Left Behind (NLLB-200) Model. The dataset used consists of 2,659 sentence pairs divided into 80% training data, 10% validation, and 10% testing. Training was carried out by comparing the results of this model with previous studies, as well as evaluating the epoch, batch size, and optimizer parameters to obtain the best accuracy. The results show that the model produces a BLEU score of 31.97 for ACE-IND and 36.16 for IND-ACE with hyperparameter tuning epoch 10, batch size 4, and RMSprop optimizer.
Keywords: Acehnese Lhokseumawe Language, Low-Resource Language, Neural Machine Translation, Transfer Learning, NLLB-200, BLEU

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2107110261

Penerbit

Pekanbaru : Universitas Riau – F.TEKNIK – INFORMATIKA., 2025

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2107110261

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TEKNIK INFORMATIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

daus

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar