@inproceedings{di-giovanni-etal-2022-datascience,
    title = "{D}ata{S}cience-Polimi at {S}em{E}val-2022 Task 8: Stacking Language Models to Predict News Article Similarity",
    author = "Di Giovanni, Marco  and
      Tasca, Thomas  and
      Brambilla, Marco",
    editor = "Emerson, Guy  and
      Schluter, Natalie  and
      Stanovsky, Gabriel  and
      Kumar, Ritesh  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      Singh, Siddharth  and
      Ratan, Shyam",
    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.semeval-1.174/",
    doi = "10.18653/v1/2022.semeval-1.174",
    pages = "1229--1234",
    abstract = "In this paper, we describe the approach we designed to solve SemEval-2022 Task 8: Multilingual News Article Similarity. We collect and use exclusively textual features (title, description and body) of articles. Our best model is a stacking of 14 Transformer-based Language models fine-tuned on single or multiple fields, using data in the original language or translated to English. It placed fourth on the original leaderboard, sixth on the complete official one and fourth on the English-subset official one. We observe the data collection as our principal source of error due to a relevant fraction of missing or wrong fields."
}