Skeleton-based Coherence Modeling in Narratives

📰 ArXiv cs.AI

Researchers propose skeleton-based coherence modeling for narrative texts using neural networks

advanced Published 6 Apr 2026

Action Steps

Extract skeletons from individual sentences using neural networks
Use the extracted skeletons to generate coherent narrative stories
Evaluate the consistency of skeletons across subsections of the narrative
Apply the coherence model to detect and fix incoherent structures in text

Who Needs to Know This

NLP researchers and AI engineers on a team can benefit from this study to improve text generation and coherence modeling, enabling them to develop more sophisticated language models

Key Insight

💡 Using neural networks to extract and generate skeletons can improve coherence in text generation

Key Takeaways

Researchers propose skeleton-based coherence modeling for narrative texts using neural networks

Full Article

Title: Skeleton-based Coherence Modeling in Narratives

Abstract:
arXiv:2604.02451v1 Announce Type: cross Abstract: Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to extract a skeleton from one sentence, and then use that skeleton to generate the next sentence for coherent narrative story generation. In this project, we aim to study if the consistency of skeletons across subs

Read full paper → ← Back to Reads