Saved in:
Bibliographic Details
Main Authors: Alabi, Jesujoba O., Azime, Israel Abebe, Zhang, Miaoran, España-Bonet, Cristina, Bawden, Rachel, Zhu, Dawei, Adelani, David Ifeoluwa, Odoje, Clement Oyeleke, Akinade, Idris, Maab, Iffat, David, Davis, Muhammad, Shamsuddeen Hassan, Putini, Neo, Ademuyiwa, David O., Caines, Andrew, Klakow, Dietrich
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.06374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909842837340160
author Alabi, Jesujoba O.
Azime, Israel Abebe
Zhang, Miaoran
España-Bonet, Cristina
Bawden, Rachel
Zhu, Dawei
Adelani, David Ifeoluwa
Odoje, Clement Oyeleke
Akinade, Idris
Maab, Iffat
David, Davis
Muhammad, Shamsuddeen Hassan
Putini, Neo
Ademuyiwa, David O.
Caines, Andrew
Klakow, Dietrich
author_facet Alabi, Jesujoba O.
Azime, Israel Abebe
Zhang, Miaoran
España-Bonet, Cristina
Bawden, Rachel
Zhu, Dawei
Adelani, David Ifeoluwa
Odoje, Clement Oyeleke
Akinade, Idris
Maab, Iffat
David, Davis
Muhammad, Shamsuddeen Hassan
Putini, Neo
Ademuyiwa, David O.
Caines, Andrew
Klakow, Dietrich
contents This paper introduces AFRIDOC-MT, a document-level multi-parallel translation dataset covering English and five African languages: Amharic, Hausa, Swahili, Yorùbá, and Zulu. The dataset comprises 334 health and 271 information technology news documents, all human-translated from English to these languages. We conduct document-level translation benchmark experiments by evaluating neural machine translation (NMT) models and large language models (LLMs) for translations between English and these languages, at both the sentence and pseudo-document levels. These outputs are realigned to form complete documents for evaluation. Our results indicate that NLLB-200 achieved the best average performance among the standard NMT models, while GPT-4o outperformed general-purpose LLMs. Fine-tuning selected models led to substantial performance gains, but models trained on sentences struggled to generalize effectively to longer documents. Furthermore, our analysis reveals that some LLMs exhibit issues such as under-generation, repetition of words or phrases, and off-target translations, especially for African languages.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AFRIDOC-MT: Document-level MT Corpus for African Languages
Alabi, Jesujoba O.
Azime, Israel Abebe
Zhang, Miaoran
España-Bonet, Cristina
Bawden, Rachel
Zhu, Dawei
Adelani, David Ifeoluwa
Odoje, Clement Oyeleke
Akinade, Idris
Maab, Iffat
David, Davis
Muhammad, Shamsuddeen Hassan
Putini, Neo
Ademuyiwa, David O.
Caines, Andrew
Klakow, Dietrich
Computation and Language
This paper introduces AFRIDOC-MT, a document-level multi-parallel translation dataset covering English and five African languages: Amharic, Hausa, Swahili, Yorùbá, and Zulu. The dataset comprises 334 health and 271 information technology news documents, all human-translated from English to these languages. We conduct document-level translation benchmark experiments by evaluating neural machine translation (NMT) models and large language models (LLMs) for translations between English and these languages, at both the sentence and pseudo-document levels. These outputs are realigned to form complete documents for evaluation. Our results indicate that NLLB-200 achieved the best average performance among the standard NMT models, while GPT-4o outperformed general-purpose LLMs. Fine-tuning selected models led to substantial performance gains, but models trained on sentences struggled to generalize effectively to longer documents. Furthermore, our analysis reveals that some LLMs exhibit issues such as under-generation, repetition of words or phrases, and off-target translations, especially for African languages.
title AFRIDOC-MT: Document-level MT Corpus for African Languages
topic Computation and Language
url https://arxiv.org/abs/2501.06374