PulseAugur
EN
LIVE 02:46:23

New research uses AI embeddings to analyze literary sequel transformations

By PulseAugur Editorial · [2 sources] ·

A new research paper proposes a method for analyzing literary transformations by treating books as points in an embedding space. The study, "Story Operators: Decomposing the Original $\to$ Sequel Transformation in Embedding Space," uses paragraph embeddings from the PG19 corpus to quantify the geometric changes between original novels and their sequels. The analysis reveals a taxonomy of sequel types, including formulaic, concentrated, and compositional, and provides insights into the structural shifts in narratives like "Tom Sawyer" to "Huckleberry Finn." AI

IMPACT This research demonstrates a novel application of AI embeddings for literary analysis, potentially opening new avenues for computational creativity and literary studies.

RANK_REASON The cluster contains a single research paper published on arXiv.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New research uses AI embeddings to analyze literary sequel transformations

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · W. Frederick Zimmerman ·

    Story Operators: Decomposing the Original $\to$ Sequel Transformation in Embedding Space

    arXiv:2606.25379v1 Announce Type: new Abstract: I treat a book as a point in a sentence-embedding space and a literary transformation as an operation on points. Given an original novel and its sequel, I ask what it takes, geometrically, to turn the first into the second. Using al…

  2. arXiv cs.CL TIER_1 English(EN) · W. Frederick Zimmerman ·

    Story Operators: Decomposing the Original $\to$ Sequel Transformation in Embedding Space

    I treat a book as a point in a sentence-embedding space and a literary transformation as an operation on points. Given an original novel and its sequel, I ask what it takes, geometrically, to turn the first into the second. Using all-mpnet-base-v2 paragraph embeddings drawn from …

RELATED TOPICS