@article{schuler-etal-2026-dialectal,
    title = "Dialectal Filtering: Synthesizing {K}urdish Corpora for Low-Resource Varieties by Utilizing ``Noise'' in Large Textual Data",
    author = "Schuler, Christian  and
      Ahmad, Raman  and
      W{\'a}ng, {\={A}}nr{\'a}n  and
      Gurgurov, Daniil  and
      Baumann, Timo  and
      Ostermann, Simon  and
      van Genabith, Josef",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.116/",
    pages = "1505--1519",
    abstract = "This work introduces a dialect-aware text filtering framework to pre-process, clean, and enhance large text corpora, creating variety-specific sub-corpora for neglected language varieties. We apply our framework to Kurdish, a language with rich dialectal diversity, which presents significant challenges for Natural Language Processing due to its low-resource status and the noisy nature of available text corpora. Leveraging lexicographic features, we assign multi-language-labels to text instances and synthesize over 130 dialect specific corpora from large ``noisy'' data sets containing unlabeled mixtures of Kurdish varieties, representing to our knowledge the largest collection of dialect-specific Kurdish NLP resources to date. This work contributes to the creation of low-resource language technology foundations, especially dialect-specific NLP applications. Specifically, we advance research on Kurdish languages by providing insights into the linguistic relationships among Kurdish varieties."
}