@inproceedings{troiano-vossen-2024-clause,
    title = "{CLAUSE}-{ATLAS}: A Corpus of Narrative Information to Scale up Computational Literary Analysis",
    author = "Troiano, Enrica  and
      Vossen, Piek T.J.M.",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.lrec-main.292/",
    pages = "3283--3296",
    abstract = "We introduce CLAUSE-ATLAS, a resource of XIX and XX century English novels annotated automatically. This corpus, which contains 41,715 labeled clauses, allows to study stories as sequences of eventive, subjective and contextual information. We use it to investigate if recent large language models, in particular gpt-3.5-turbo with 16k tokens of context, constitute promising tools to annotate large amounts of data for literary studies (we show that this is the case). Moreover, by analyzing the annotations so collected, we find that our clause-based approach to literature captures structural patterns within books, as well as qualitative differences between them."
}