FeedBagel

All Topics

Art

GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study

Gaspard Michel

1mo ago

Source

DeezerGraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Studynewsroom-deezer.com

Snippet from the RSS feed

Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another crucial aspect: the textual context in which characters interact. We introduce Dynamic Heterogeneous Character Networks (DHCNs), which organize long novels into temporally localized heterogeneous graphs that align characters with their textual contexts. We extract […] The post GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study appeared first on Deezer Newsroom .

You might also wanna read

Analyzing Gamebooks Through Graph Theory and Network Algorithms

This article explores the connection between gamebooks (interactive books where readers make choices that determine the narrative path) and

notes.atomutek.org·9mo ago

Using Claude Code for Syntopic Reading Across 100 Non-Fiction Books

The article describes an experimental approach to using LLMs (specifically Claude Code) for deeper reading and analysis across multiple book

pieterma.es·5mo ago

Graph Convolutional Networks for Unified Document Line and Paragraph Detection

This research paper presents a unified approach for detecting lines and paragraphs in documents using graph convolutional networks. The meth

arxiv.org·9mo ago

Research on Hierarchical JSON Representations for Preserving Scientific Sentence Meaning

This research paper investigates whether structured hierarchical JSON representations can effectively preserve the meaning of scientific sen

arxiv.org·2mo ago

Research Reveals LLMs Contain Built-In Persona Subnetworks Without External Training

This research paper reveals that large language models (LLMs) already contain specialized persona subnetworks within their parameter space,

arxiv.org·4mo ago

RAGP: A Graph-Based Prompt Compression Method Using Lévy Walk-Guided Pruning

This paper introduces RAGP (Redundancy-Aware Graph Pruning), a novel prompt compression method that treats text as a multiplex graph rather

arxiv.org·1d ago

Comments

No comments yet. Be the first.