@inproceedings{nasir-mchechesi-2022-geographical,
    title = "Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For {E}nglish-isi{Z}ulu Machine Translation.",
    author = "Nasir, Muhammad Umair  and
      Mchechesi, Innocent",
    editor = "Asai, Akari  and
      Choi, Eunsol  and
      Clark, Jonathan H.  and
      Hu, Junjie  and
      Lee, Chia-Hsuan  and
      Kasai, Jungo  and
      Longpre, Shayne  and
      Yamada, Ikuya  and
      Zhang, Rui",
    booktitle = "Proceedings of the Workshop on Multilingual Information Access (MIA)",
    month = jul,
    year = "2022",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/build-pipeline-with-new-library/2022.mia-1.1/",
    doi = "10.18653/v1/2022.mia-1.1",
    pages = "1--8",
    abstract = "Stemming from the limited availability of datasets and textual resources for low-resource languages such as isiZulu, there is a significant need to be able to harness knowledge from pre-trained models to improve low resource machine translation. Moreover, a lack of techniques to handle the complexities of morphologically rich languages has compounded the unequal development of translation models, with many widely spoken African languages being left behind. This study explores the potential benefits of transfer learning in an English-isiZulu translation framework. The results indicate the value of transfer learning from closely related languages to enhance the performance of low-resource translation models, thus providing a key strategy for low-resource translation going forward. We gathered results from 8 different language corpora, including one multi-lingual corpus, and saw that isiXhosa-isiZulu outperformed all languages, with a BLEU score of 8.56 on the test set which was better from the multi-lingual corpora pre-trained model by 2.73. We also derived a new coefficient, Nasir's Geographical Distance Coefficient (NGDC) which provides an easy selection of languages for the pre-trained models. NGDC also indicated that isiXhosa should be selected as the language for the pre-trained model."
}