@inproceedings{saleva-lignos-2021-effectiveness,
    title = "The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation",
    author = "Saleva, Jonne  and
      Lignos, Constantine",
    editor = "Sorodoc, Ionut-Teodor  and
      Sushil, Madhumita  and
      Takmaz, Ece  and
      Agirre, Eneko",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.eacl-srw.22/",
    doi = "10.18653/v1/2021.eacl-srw.22",
    pages = "164--174",
    abstract = "This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations from LMVR and MORSEL. We evaluate translation tasks between English and each of Nepali, Sinhala, and Kazakh, and predict that using morphologically-based segmentation methods would lead to better performance in this setting. However, comparing to BPE, we find that no consistent and reliable differences emerge between the segmentation methods. While morphologically-based methods outperform BPE in a few cases, what performs best tends to vary across tasks, and the performance of segmentation methods is often statistically indistinguishable."
}