@inproceedings{rabus-scherrer-2017-lexicon,
    title = "Lexicon Induction for Spoken {R}usyn {--} Challenges and Results",
    author = "Rabus, Achim  and
      Scherrer, Yves",
    editor = "Erjavec, Toma{\v{z}}  and
      Piskorski, Jakub  and
      Pivovarova, Lidia  and
      {\v{S}}najder, Jan  and
      Steinberger, Josef  and
      Yangarber, Roman",
    booktitle = "Proceedings of the 6th Workshop on {B}alto-{S}lavic Natural Language Processing",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W17-1405/",
    doi = "10.18653/v1/W17-1405",
    pages = "27--32",
    abstract = "This paper reports on challenges and results in developing NLP resources for spoken Rusyn. Being a Slavic minority language, Rusyn does not have any resources to make use of. We propose to build a morphosyntactic dictionary for Rusyn, combining existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish. We adapt these resources to Rusyn by using vowel-sensitive Levenshtein distance, hand-written language-specific transformation rules, and combinations of the two. Compared to an exact match baseline, we increase the coverage of the resulting morphological dictionary by up to 77.4{\%} relative (42.9{\%} absolute), which results in a tagging recall increased by 11.6{\%} relative (9.1{\%} absolute). Our research confirms and expands the results of previous studies showing the efficiency of using NLP resources from neighboring languages for low-resourced languages."
}