@inproceedings{suppa-adamec-2020-summarization,
    title = "A Summarization Dataset of {S}lovak News Articles",
    author = "Suppa, Marek  and
      Adamec, Jergus",
    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
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.lrec-1.830/",
    pages = "6725--6730",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "As a well established NLP task, single-document summarization has seen significant interest in the past few years. However, most of the work has been done on English datasets. This is particularly noticeable in the context of evaluation where the dominant ROUGE metric assumes its input to be written in English. In this paper we aim to address both of these issues by introducing a summarization dataset of articles from a popular Slovak news site and proposing small adaptation to the ROUGE metric that make it better suited for Slovak texts. Several baselines are evaluated on the dataset, including an extractive approach based on the Multilingual version of the BERT architecture. To the best of our knowledge, the presented dataset is the first large-scale news-based summarization dataset for text written in Slovak language. It can be reproduced using the utilities available at \url{https://github.com/NaiveNeuron/sme-sum}"
}