@inproceedings{zheng-etal-2022-parallel,
    title = "A Parallel Corpus and Dictionary for {A}mis-{M}andarin Translation",
    author = "Zheng, Francis  and
      Marrese-Taylor, Edison  and
      Matsuo, Yutaka",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      Alnajjar, Khalid  and
      Partanen, Niko  and
      Rueter, Jack},
    booktitle = "Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities",
    month = nov,
    year = "2022",
    address = "Taipei, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2022.nlp4dh-1.11/",
    doi = "10.18653/v1/2022.nlp4dh-1.11",
    pages = "79--84",
    abstract = "Amis is an endangered language indigenous to Taiwan with limited data available for computational processing. We thus present an Amis-Mandarin dataset containing a parallel corpus of 5,751 Amis and Mandarin sentences and a dictionary of 7,800 Amis words and phrases with their definitions in Mandarin. Using our dataset, we also established a baseline for machine translation between Amis and Mandarin in both directions. Our dataset can be found at \url{https://github.com/francisdzheng/amis-mandarin}."
}