Skip to Main content Skip to Navigation
Conference papers

The effect of domain and diacritics in Yorùbá-English neural machine translation

Abstract : Massively multilingual machine translation (MT) has shown impressive capabilities, including zero and few-shot translation between low-resource language pairs. However, these models are often evaluated on high-resource languages with the assumption that they generalize to low-resource ones. The difficulty of evaluating MT models on low-resource pairs is often due to lack of standardized evaluation datasets. In this paper, we present MENYO-20k, the first multi-domain parallel corpus with a special focus on clean orthography for Yorùbá-English with standardized train-test splits for benchmarking. We provide several neural MT benchmarks and compare them to the performance of popular pre-trained (massively multilingual) MT models both for the heterogeneous test set and its subdomains. Since these pre-trained models use huge amounts of data with uncertain quality, we also analyze the effect of diacritics, a major characteristic of Yorùbá, in the training data. We investigate how and when this training condition affects the final quality and intelligibility of a translation. Our models outperform massively multilingual models such as Google (+8.7 BLEU) and Facebook M2M (+9.1 BLEU) when translating to Yorùbá, setting a high quality benchmark for future research.
Document type :
Conference papers
Complete list of metadata
Contributor : Emmanuel Vincent Connect in order to contact the contributor
Submitted on : Tuesday, September 21, 2021 - 8:17:30 PM
Last modification on : Thursday, September 23, 2021 - 3:08:08 AM
Long-term archiving on: : Wednesday, December 22, 2021 - 7:20:59 PM


Files produced by the author(s)


  • HAL Id : hal-03350967, version 1



David Ifeoluwa Adelani, Dana Ruiter, Jesujoba O Alabi, Damilola Adebonojo, Adesina Ayeni, et al.. The effect of domain and diacritics in Yorùbá-English neural machine translation. 18th Biennial Machine Translation Summit, Aug 2021, Orlando, United States. ⟨hal-03350967⟩



Record views


Files downloads