@article{ahmadi2022leveraging,
      author = {Ahmadi, Sina and Hassani, Hossein and Jaff, Daban Q.},
      title = {Leveraging Multilingual News Websites for Building a {K}urdish Parallel Corpus},
      year = {2022},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA},
      issn = {2375-4699},
      url = {https://doi.org/10.1145/3511806},
      doi = {10.1145/3511806},
      abstract = {Machine translation has been a major motivation of development in natural language processing. Despite the burgeoning achievements in creating more efficient machine translation systems thanks to deep learning methods, parallel corpora have remained indispensable for progress in the field. In an attempt to create parallel corpora for the Kurdish language, in this paper, we describe our approach in retrieving potentially-alignable news articles from multi-language websites and manually align them across dialects and languages based on lexical similarity and transliteration of scripts. We present a corpus containing 12,327 translation pairs in the two major dialects of Kurdish, Sorani and Kurmanji. We also provide 1,797 and 650 translation pairs in English-Kurmanji and English-Sorani. The corpus is publicly available under the CC BY-NC-SA 4.0 license.1},
      note = {Just Accepted},
      journal = {ACM Trans. Asian Low-Resour. Lang. Inf. Process.},
      month = {jan},
      keywords = {machine translation, parallel corpus, natural language processing, Kurdish, less-resourced languages}
}