@inproceedings{chen-etal-2023-symbolization,
    title = "Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels",
    author = "Chen, Yue  and
      He, Tianwei  and
      Zhou, Hongbin  and
      Gu, Jia-Chen  and
      Lu, Heng  and
      Ling, Zhen-Hua",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.findings-emnlp.225/",
    doi = "10.18653/v1/2023.findings-emnlp.225",
    pages = "3455--3467",
    abstract = "Speaker identification in novel dialogues can be widely applied to various downstream tasks, such as producing multi-speaker audiobooks and converting novels into scripts. However, existing state-of-the-art methods are limited to handling explicit narrative patterns like {\textquotedblleft}Tom said, '...''', unable to thoroughly understand long-range contexts and to deal with complex cases. To this end, we propose a framework named SPC, which identifies implicit speakers in novels via symbolization, prompt, and classification. First, SPC symbolizes the mentions of candidate speakers to construct a unified label set. Then, by inserting a prompt we re-formulate speaker identification as a classification task to minimize the gap between the training objectives of speaker identification and the pre-training task. Two auxiliary tasks are also introduced in SPC to enhance long-range context understanding. Experimental results show that SPC outperforms previous methods by a large margin of 4.8{\%} accuracy on the web novel collection, which reduces 47{\%} of speaker identification errors, and also outperforms the emerging ChatGPT. In addition, SPC is more accurate in implicit speaker identification cases that require long-range context semantic understanding."
}