@inproceedings{gongora-etal-2022-use,
    title = "Can We Use Word Embeddings for Enhancing {G}uarani-{S}panish Machine Translation?",
    author = "G{\'o}ngora, Santiago  and
      Giossa, Nicol{\'a}s  and
      Chiruzzo, Luis",
    editor = "Moeller, Sarah  and
      Anastasopoulos, Antonios  and
      Arppe, Antti  and
      Chaudhary, Aditi  and
      Harrigan, Atticus  and
      Holden, Josh  and
      Lachler, Jordan  and
      Palmer, Alexis  and
      Rijhwani, Shruti  and
      Schwartz, Lane",
    booktitle = "Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.computel-1.16/",
    doi = "10.18653/v1/2022.computel-1.16",
    pages = "127--132",
    abstract = "Machine translation for low-resource languages, such as Guarani, is a challenging task due to the lack of data. One way of tackling it is using pretrained word embeddings for model initialization. In this work we try to check if currently available data is enough to train rich embeddings for enhancing MT for Guarani and Spanish, by building a set of word embedding collections and training MT systems using them. We found that the trained vectors are strong enough to slightly improve the performance of some of the translation models and also to speed up the training convergence."
}