@inproceedings{devatine-etal-2023-melodi,
    title = "{MELODI} at {S}em{E}val-2023 Task 3: In-domain Pre-training for Low-resource Classification of News Articles",
    author = "Devatine, Nicolas  and
      Muller, Philippe  and
      Braud, Chlo{\'e}",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.semeval-1.14/",
    doi = "10.18653/v1/2023.semeval-1.14",
    pages = "108--113",
    abstract = "This paper describes our approach to Subtask 1 {\textquotedblleft}News Genre Categorization{\textquotedblright} of SemEval-2023 Task 3 {\textquotedblleft}Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multi-lingual Setup{\textquotedblright}, which aims to determine whether a given news article is an opinion piece, an objective report, or satirical. We fine-tuned the domain-specific language model POLITICS, which was pre-trained on a large-scale dataset of more than 3.6M English political news articles following ideology-driven pre-training objectives. In order to use it in the multilingual setup of the task, we added as a pre-processing step the translation of all documents into English. Our system ranked among the top systems overall in most language, and ranked 1st on the English dataset."
}