@inproceedings{gobara-etal-2025-speaker,
    title = "Speaker Identification and Dataset Construction Using {LLM}s: A Case Study on {J}apanese Narratives",
    author = "Gobara, Seiji  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    editor = "Clark, Elizabeth  and
      Lal, Yash Kumar  and
      Chaturvedi, Snigdha  and
      Iyyer, Mohit  and
      Brei, Anneliese  and
      Modi, Ashutosh  and
      Chandu, Khyathi Raghavi",
    booktitle = "Proceedings of the The 7th Workshop on Narrative Understanding",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.wnu-1.17/",
    pages = "97--119",
    ISBN = "979-8-89176-247-3",
    abstract = "Speaker identification in narrative analysis is a challenging task due to complex dialogues, diverse utterance patterns, and ambiguous character references. Cosly and time-intensive manual annotation limits the scalability of high-quality dataset creation.This study demonstrates a cost-efficient approach of constructing speaker identification datasets by combining small-scale manual annotation with LLM-based labeling. A subset of data is manually annotated and is used to guide LLM predictions with a few-shot approach followed by refinement through minimal human corrections. Our results show that LLMs achieve approximately 90{\%} accuracy on challenging narratives, such as the ``Three Kingdoms'' dataset, underscoring the importance of targeted human corrections. This approach proves effective for constructing scalable and cost-efficient datasets for Japanese and complex narratives."
}