Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

Stammbach, Dominik; Antoniak, Maria; Ash, Elliott

doi:10.48550/arxiv.2205.07557

Cited by 2 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, for example, labeling documents as belonging to a category, or having some feature, should be possible with GPT-like models, perhaps with additional human supervision (e.g., Gilardi et al 2023, Hansen et al 2023. Stammbach et al (2022) illustrate this possibility in the case of identifying narrative roles in texts-that is, extracting heroes, villains, and victims from plain-text stories. In order to make most effective use of large language models, researchers must take care to design appropriate prompts.…”

Section: Possibilities Of Large Pretrained Language Modelsmentioning

confidence: 99%

Text Algorithms in Economics

Ash

Hansen

2023

Annual Review of Economics

View full text Add to dashboard Cite

This article provides an overview of the methods used for algorithmic text analysis in economics, with a focus on three key contributions. First, we introduce methods for representing documents as high-dimensional count vectors over vocabulary terms, for representing words as vectors, and for representing word sequences as embedding vectors. Second, we define four core empirical tasks that encompass most text-as-data research in economics and enumerate the various approaches that have been taken so far to accomplish these tasks. Finally, we flag limitations in the current literature, with a focus on the challenge of validating algorithmic output. Expected final online publication date for the Annual Review of Economics, Volume 15 is August 2023. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

show abstract

Section: Possibilities Of Large Pretrained Language Modelsmentioning

confidence: 99%

Text Algorithms in Economics

Ash

Hansen

2023

Annual Review of Economics

View full text Add to dashboard Cite

show abstract

“…Such a definition can be useful because it highlights the array of narrative elements that require computational solutions to "understand" the cultural meaning of a story. Such applications have included: character detection (Bamman et al, 2014;Jahan et al, 2018;Piper, 2023b;Stammbach et al, 2022), object detection (Piper and Bagga, 2022a), character relation detection (Labatut and Bost, 2019;Kraicer and Piper, 2019), event detection (Vauth et al, 2021), geographic and spatial understanding (Wilkens, 2013;Evans and Wilkens, 2018;Piatti et al, 2013;Erlin et al, 2021), temporal understanding (Underwood, 2018;Yauney et al, 2019;Vossen et al, 2021;Gangal et al, 2022), and causality mining (Meehan and Piper, 2022). A full review can be found in and Santana et al (2023).…”

Section: The Elements Of Narrativementioning

confidence: 99%

Computational Narrative Understanding: A Big Picture Analysis

Piper

2023

Proceedings of the Big Picture Workshop

View full text Add to dashboard Cite

This paper provides an overview of outstanding major research goals for the field of computational narrative understanding. Storytelling is an essential human practice, one that provides a sense of personal meaning, shared sense of community, and individual enjoyment. A number of research domains have increasingly focused on storytelling as a key mechanism for explaining human behavior. Now is an opportune moment to provide a vision of the contributions that computational narrative understanding can make towards this collective endeavor and the challenges facing the field. In addition to providing an overview of the elements of narrative, this paper outlines three major lines of inquiry: understanding the multimodality of narrative; the temporal patterning of narrative (narrative "shape"); and sociocultural narrative schemas, i.e. collective narratives. The paper concludes with a call for more inter-disciplinary working groups and deeper investment in building cross-cultural and multimodal narrative datasets.

show abstract

Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

Cited by 2 publications

References 22 publications

Text Algorithms in Economics

Text Algorithms in Economics

Computational Narrative Understanding: A Big Picture Analysis

Contact Info

Product

Resources

About