Neural Machine Translation for Amharic-English Translation
Domain:
natural language processingRecord type:
paper
This paper describes neural machine translation between orthographically and morphologically divergent
languages. Amharic has a rich morphology; it uses the syllabic Ethiopic script. We used a new transliteration
technique for Amharic to facilitate vocabulary sharing. To tackle the highly inflectional morphology and to
make an open vocabulary translation, we used subwords. Furthermore, the research was conducted on lowdata conditions. We used the transformer-based neural machine translation architecture by tuning the
hyperparameters for low-data conditions. In the automatic evaluation of the strong baseline, word-based, and
subword-based models trained on a public benchmark dataset, the best subword-based models outperform the
baseline models by approximately six up to seven BLEU.
Similar
Amharic-English Parallel Corpus for Neural Machine TranslationAmharic-Arabic Neural Machine TranslationThe Effect of Normalization for Bi-directional Amharic-English Neural Machine TranslationEnglish-Amharic Statistical Machine TranslationAmharic-English-Machine-Translation-Corpusabenezermtu/Amharic-English-Machine-Translation