# Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings

arXiv: https://arxiv.org/abs/2103.04225 · HTML: https://mlsanity.com/paper/2103.04225/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 7 Mar 2021.

## Builds on (most cited first, 19 of 19)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://mlsanity.com/paper/1805.10163/) (2018)
- [Evaluating Discourse Phenomena in Neural Machine Translation](https://mlsanity.com/paper/1711.00513/) (2017)
- [Revisiting Low-Resource Neural Machine Translation: A Case Study](https://mlsanity.com/paper/1905.11901/) (2019)
- [Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation](https://mlsanity.com/paper/1708.09803/) (2017)
- [Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation](https://mlsanity.com/paper/1906.12068/) (2019)
- [How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs](https://mlsanity.com/paper/1612.04629/) (2016)
- [A Challenge Set Approach to Evaluating Machine Translation](https://mlsanity.com/paper/1704.07431/) (2017)
- [Neural versus Phrase-Based Machine Translation Quality: a Case Study](https://mlsanity.com/paper/1608.04631/) (2016)
- [A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions](https://mlsanity.com/paper/1701.02901/) (2017)
- [Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions](https://mlsanity.com/paper/1610.01108/) (2016)
- [Deep Architectures for Neural Machine Translation](https://mlsanity.com/paper/1707.07631/) (2017)
- [Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction](https://mlsanity.com/paper/1911.12091/) (2019)
- [Fine-grained human evaluation of neural versus phrase-based machine translation](https://mlsanity.com/paper/1706.04389/) (2017)

## Built on by (most cited first, 5 of 5)

- [Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialects](https://mlsanity.com/paper/2406.19564/) (2024)
- [IndT5: A Text-to-Text Transformer for 10 Indigenous Languages](https://mlsanity.com/paper/2104.07483/) (2021)
- [Improving Similar Language Translation With Transfer Learning](https://mlsanity.com/paper/2108.03533/) (2021)
- [Machine Translation of Low-Resource Indo-European Languages](https://mlsanity.com/paper/2108.03739/) (2021)
- [NaijaNLP: A Survey of Nigerian Low-Resource Languages](https://mlsanity.com/paper/2502.19784/) (2025)

## Abstract (arXiv)

Translating between languages where certain features are marked morphologically in one but absent or marked contextually in the other is an important test case for machine translation. When translating into English which marks (in)definiteness morphologically, from Yor`ub'a which uses bare nouns but marks these features contextually, ambiguities arise. In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yor`ub'a into English. We investigate how the systems what extent they identify BNs, correctly translate them, and compare with human translation patterns. We also analyze the type of errors each model makes and provide a linguistic description of these errors. We glean insights for evaluating model performance in low-resource settings. In translating bare nouns, our results show the transformer model outperforms the SMT and BiLSTM models for 4 categories, the BiLSTM outperforms the SMT model for 3 categories while the SMT outperforms the NMT models for 1 category.