Better Low-Resource Machine Translation with Smaller Vocabularies
| Authors | |
|---|---|
| Year of publication | 2024 |
| Type | Article in Proceedings |
| Conference | Text, Speech, and Dialogue |
| MU Faculty or unit | |
| Citation | |
| Web | https://link.springer.com/chapter/10.1007/978-3-031-70563-2_15 |
| Doi | http://dx.doi.org/10.1007/978-3-031-70563-2_15 |
| Keywords | Low-resource;Neural Machine Translation;Tokenization |
| Attached files | |
| Description | Data scarcity is still a major challenge in machine translation. The performance of state-of-the-art deep learning architectures, such as the Transformers, for under-resourced languages is well below the one for high-resourced languages. This precludes access to information for millions of speakers across the globe. Previous research has shown that the Transformer is highly sensitive to hyperparameters in low-resource conditions. One such parameter is the size of the subword vocabulary of the model. In this paper, we show that using smaller vocabularies, as low as 1k tokens, instead of the default value of 32k, is preferable in a diverse array of low-resource conditions. We experiment with different sizes on English-Akkadian, Lower Sorbian-German, English-Manipuri, to obtain models that are faster to train, smaller, and better performing than the default setting. These models achieve improvements of up to 322% ChrF score, while being up to 66% smaller and up to 17% faster to train. |
| Related projects: |