@inproceedings{zhou-etal-2024-mainlp,
    title = "{M}ai{NLP} at {S}em{E}val-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness",
    author = "Zhou, Shijia  and
      Shan, Huangyan  and
      Plank, Barbara  and
      Litschko, Robert",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2024.semeval-1.259/",
    doi = "10.18653/v1/2024.semeval-1.259",
    pages = "1842--1853",
    abstract = "This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. The task aims to detect semantic relatedness of two sentences from the same languages. For cross-lingual approach we developed a set of linguistics-inspired models trained with several task-specific strategies. We 1) utilize language vectors for selection of donor languages; 2) investigate the multi-source approach for training; 3) use transliteration of non-latin script to study impact of {\textquotedblleft}script gap{\textquotedblright}; 4) opt machine translation for data augmentation. We additionally compare the performance of XLM-RoBERTa and Furina with the same training strategy. Our submission achieved the first place in the C8 (Kinyarwanda) test."
}