@inproceedings{tian-etal-2025-ruc,
    title = "{RUC} Team at {S}em{E}val-2025 Task 5: Fast Automated Subject Indexing: A Method Based on Similar Records Matching and Related Subject Ranking",
    author = "Tian, Xia  and
      Xin, Yang  and
      Jing, Wu  and
      Heng, Xiu  and
      Xin, Zhang  and
      Yu, Li  and
      Tong, Gao  and
      Xi, Tan  and
      Dong, Hu  and
      Tao, Chen  and
      Zhi, Jia",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.317/",
    pages = "2437--2442",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents MaRSI, an automatic subject indexing method designed to address the limitations of traditional manual indexing and emerging GenAI technologies. Focusing on improving indexing accuracy in cross-lingual contexts and balancing efficiency and accuracy in large-scale datasets, MaRSI mimics human reference learning behavior by constructing semantic indexes from pre-indexed document. It calculates similarity to retrieve relevant references, merges, and reorders their topics to generate index results. Experiments demonstrate that MaRSI outperforms supervised fine-tuning of LLMs on the same dataset, offering advantages in speed, effectiveness, and interpretability."
}