Assessing Human Translations from French to Bambara for Machine Learning: a Pilot Study

TL;DR

This study introduces new methods for evaluating human translations from French to Bambara, highlighting that both written and oral translations can be equally effective for machine learning, and offers guidelines to enhance translation quality.

Contribution

It presents novel assessment techniques for human-translated texts in under-resourced languages and provides practical instructions to improve translation quality for machine learning.

Findings

Similar quality from written and oral translations for certain texts

Specific instructions improve translation quality

Guidelines for better human translation in under-resourced languages

Abstract

We present novel methods for assessing the quality of human-translated aligned texts for learning machine translation models of under-resourced languages. Malian university students translated French texts, producing either written or oral translations to Bambara. Our results suggest that similar quality can be obtained from either written or spoken translations for certain kinds of texts. They also suggest specific instructions that human translators should be given in order to improve the quality of their work.