Extended Parallel Corpus for Amharic-English Machine Translation

TL;DR

This paper presents a new Amharic-English parallel corpus and baseline translation models, demonstrating neural models' superior performance over statistical ones, especially with subword units, for low-resource language translation.

Contribution

It introduces a publicly available Amharic-English corpus and compares statistical and neural translation models, highlighting the effectiveness of neural subword models.

Findings

Neural machine translation outperforms statistical models by 6-7 BLEU points.

Subword models outperform word-based models by 3-4 BLEU points.

Automatic metrics confirm neural and subword models' superior performance.

Abstract

This paper describes the acquisition, preprocessing, segmentation, and alignment of an Amharic-English parallel corpus. It will be helpful for machine translation of a low-resource language, Amharic. We freely released the corpus for research purposes. Furthermore, we developed baseline statistical and neural machine translation systems; we trained statistical and neural machine translation models using the corpus. In the experiments, we also used a large monolingual corpus for the language model of statistical machine translation and back-translation of neural machine translation. In the automatic evaluation, neural machine translation models outperform statistical machine translation models by approximately six to seven Bilingual Evaluation Understudy (BLEU) points. Besides, among the neural machine translation models, the subword models outperform the word-based models by three to four BLEU points. Moreover, two other relevant automatic evaluation metrics, Translation Edit Rate on Character Level and Better Evaluation as Ranking, reflect corresponding differences among the trained models.