Portrayal: Leveraging NLP and Visualization for Analyzing Fictional Characters

MN Hoque, B Ghai, K Kraus, N Elmqvist - Proceedings of the 2023 ACM …, 2023 - dl.acm.org
Many creative writing tasks (eg, fiction writing) require authors to write complex narrative
components (eg, characterization, events, dialogue) over the course of a long story …

Major Entity Identification: A Generalizable Alternative to Coreference Resolution

K Manikantan, S Toshniwal, M Tapaswi… - arXiv preprint arXiv …, 2024 - arxiv.org
The limited generalization of coreference resolution (CR) models has been a major
bottleneck in the task's broad application. Prior work has identified annotation differences …

KoCoNovel: Annotated Dataset of Character Coreference in Korean Novels

K Kim, S Lee, S Lee - arXiv preprint arXiv:2404.01140, 2024 - arxiv.org
We present KoCoNovel, an novel character coreference dataset derived from Korean literary
texts, complete with detailed annotation guidelines. Comprising 178K tokens from 50 …

Big data meets storytelling: using machine learning to predict popular fanfiction

D Nguyen, S Zigmond, S Glassco, B Tran… - Social Network Analysis …, 2024 - Springer
Fanfictions are a popular literature genre in which writers reuse a universe, for example to
transform heteronormative relationships with queer characters or to bring romance into …

Major Entity Identification: A Generalizable Alternative to Coreference Resolution

K Sundar, S Toshniwal, M Tapaswi… - Proceedings of the 2024 …, 2024 - aclanthology.org
The limited generalization of coreference resolution (CR) models has been a major
bottleneck in the task's broad application. Prior work has identified annotation differences …

[Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs

RMM Hicke, D Mimno - arXiv preprint arXiv:2401.17922, 2024 - arxiv.org
Coreference annotation and resolution is a vital component of computational literary studies.
However, it has previously been difficult to build high quality systems for fiction. Coreference …

IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark

K Manikantan, M Tapaswi, V Gandhi… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent evaluations of LLMs on coreference resolution have revealed that traditional output
formats and evaluation metrics do not fully capture the models' referential understanding. To …

Enhancing character type detection using coreference information: experiments on dramatic texts

J Pagel - 2024 - elib.uni-stuttgart.de
This thesis describes experiments on enhancing machine-learning based detection of
literary character types in German-language dramatic texts by using coreference …