Evaluating Native-Speaker Preferences on Machine Translation and Post-Edits for Five African Languages

Read full text Summarise with VIRAT
Authors: Hiba El Oirghi, Tajuddeen Gwadabe, Marine Jacinthe Carpuat
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Wikipedia editors undertake the task of editing machine translation (MT) outputs in various languages to disseminate multilingual knowledge from English.But are editors doing more than just translating or fixing MT output?To answer this broad question, we constructed a dataset of 4,335 fine-grained annotated parallel pairs of MT translations and human post-edit (HE) translations for five low-resource African languages: Hausa, Igbo, Swahili, Yoruba, and Zulu.We report on our data selection and annotation methodologies as well as findings from the annotated dataset, the most surprising of which is that annotators mostly preferred the MT translations over their HE counterparts for three out of five languages.We analyze the nature of these "fluency breaking" edits and provide recommendations for the MT post-editing workflows in the Wikipedia domain and beyond.

Fields of Study & Subjects

Natural Language Processing Techniques Translation Studies and Practices Topic Modeling

Publication details

Journal / source
Workshop on African Natural Language Processing (AfricaNLP)
Pages
163–170
Publication date
1 January 2026
Language
EN