Replicable Benchmarking of Neural Machine Translation for Low-Resource Local Languages in Indonesia
Published in SEALP 2023 Workshop in IJCNLP-AACL 2023, 2023
Recommended citation: Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia". Lucky Susanto, Ryandito Diandaru, Adila Krisnadhi, Ayu Purwarianti, Derry Wijaya. In the First Workshop in South East Asian Language Processing (SEALP), 2023. hhttps://arxiv.org/abs/2311.00998
Benchmarking potential breakthroughs became a challenge due to the high-resource settings many models utilize. However, using weak baselines are not a convincing way in showing the impact of a breakthrough. So, we created a replicable benchmarking of NMT for low-resource local languages in Indonesia made using only one GPU and utilizing only 96 hours per model.