@inproceedings{fernandez-adlaon-2022-exploring,
    title = "Exploring Word Alignment towards an Efficient Sentence Aligner for {F}ilipino and {C}ebuano Languages",
    author = "Fernandez, Jenn Leana  and
      Adlaon, Kristine Mae M.",
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-Hong  and
      Vylomova, Ekaterina  and
      Abbott, Jade  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Pirinen, Tommi A  and
      Malykh, Valentin  and
      Logacheva, Varvara  and
      Zhao, Xiaobing",
    booktitle = "Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.loresmt-1.13/",
    pages = "99--106",
    abstract = "Building a robust machine translation (MT) system requires a large amount of parallel corpus which is an expensive resource for low-resourced languages. The two major languages being spoken in the Philippines which are Filipino and Cebuano have an abundance in monolingual data that this study took advantage of attempting to find the best way to automatically generate parallel corpus out from monolingual corpora through the use of bitext alignment. Byte-pair encoding was applied in an attempt to optimize the alignment of the source and target texts. Results have shown that alignment was best achieved without segmenting the tokens. Itermax alignment score is best for short-length sentences and match or argmax alignment score are best for long-length sentences."
}