@inproceedings{abdulrahman-etal-2019-developing,
    title = "Developing a Fine-grained Corpus for a Less-resourced Language: the case of {K}urdish",
    author = "Abdulrahman, Roshna  and
      Hassani, Hossein  and
      Ahmadi, Sina",
    editor = "Axelrod, Amittai  and
      Yang, Diyi  and
      Cunha, Rossana  and
      Shaikh, Samira  and
      Waseem, Zeerak",
    booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-3634/",
    pages = "106--109",
    abstract = "Kurdish is a less-resourced language consisting of different dialects written in various scripts. Approximately 30 million people in different countries speak the language. The lack of corpora is one of the main obstacles in Kurdish language processing. In this paper, we present KTC-the Kurdish Textbooks Corpus, which is composed of 31 K-12 textbooks in Sorani dialect. The corpus is normalized and categorized into 12 educational subjects containing 693,800 tokens (110,297 types). Our resource is publicly available for non-commercial use under the CC BY-NC-SA 4.0 license."
}