The Effect of Domain and Diacritics in Yorùbá-English Neural Machine Translation
arXiv:2103.08647
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 ( BLEU) and Facebook M2M ( BLEU) when translating to Yorùbá, setting a high quality benchmark for future research.
Accepted to MT Summit 2021 (Research Track)
References in corpus (9)
- On Using Monolingual Corpora in Neural Machine Translation
- Beyond English-Centric Multilingual Machine Translation
- Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
- Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
- A Focus on Neural Machine Translation for African Languages
- Igbo-English Machine Translation: An Evaluation Benchmark
- AI4D -- African Language Program
- Improving Yorùbá Diacritic Restoration
- Evaluating Amharic Machine Translation