@inproceedings{carik-yeniterzi-2022-twitter,
    title = "A {T}witter Corpus for Named Entity Recognition in {T}urkish",
    author = "{\c{C}}ar{\i}k, Buse  and
      Yeniterzi, Reyyan",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.lrec-1.484/",
    pages = "4546--4551",
    abstract = "This paper introduces a new Turkish Twitter Named Entity Recognition dataset. The dataset, which consists of 5000 tweets from a year-long period, was labeled by multiple annotators with a high agreement score. The dataset is also diverse in terms of the named entity types as it contains not only person, organization, and location but also time, money, product, and tv-show categories. Our initial experiments with pretrained language models (like BertTurk) over this dataset returned F1 scores of around 80{\%}. We share this dataset publicly."
}