# Translating Similar Languages: Role of Mutual Intelligibility in Multilingual Transformers

arXiv: https://arxiv.org/abs/2011.05037 · HTML: https://mlsanity.com/paper/2011.05037/

## Key facts

- Cited by 6 papers in the map (data through 13 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [IndT5: A Text-to-Text Transformer for 10 Indigenous Languages](https://mlsanity.com/paper/2104.07483/) (2021)
- [SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification](https://mlsanity.com/paper/2303.09421/) (2023)
- [Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Study](https://mlsanity.com/paper/2404.08259/) (2024)
- [Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation](https://mlsanity.com/paper/2104.05848/) (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)

## Abstract (arXiv)

We investigate different approaches to translate between similar languages under low resource conditions, as part of our contribution to the WMT 2020 Similar Languages Translation Shared Task. We submitted Transformer-based bilingual and multilingual systems for all language pairs, in the two directions. We also leverage back-translation for one of the language pairs, acquiring an improvement of more than 3 BLEU points. We interpret our results in light of the degree of mutual intelligibility (based on Jaccard similarity) between each pair, finding a positive correlation between mutual intelligibility and model performance. Our Spanish-Catalan model has the best performance of all the five language pairs. Except for the case of Hindi-Marathi, our bilingual models achieve better performance than the multilingual models on all pairs.