Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Černý, Jan, Kvapilíková, Ivana, Cinková, Silvie
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911362649686016
author Černý, Jan
Kvapilíková, Ivana
Cinková, Silvie
author_facet Černý, Jan
Kvapilíková, Ivana
Cinková, Silvie
contents This work investigates how measuring information entropy of text can be used to estimate its readability. We propose a visualization framework that can be used to approximate information entropy of text using multiple language models and visualize the result. The end goal is to use this method to estimate and improve readability and clarity of administrative or bureaucratic texts. Our toolset is available as a libre software on https://github.com/ufal/Glitter.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05411
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts
Černý, Jan
Kvapilíková, Ivana
Cinková, Silvie
Computation and Language
This work investigates how measuring information entropy of text can be used to estimate its readability. We propose a visualization framework that can be used to approximate information entropy of text using multiple language models and visualize the result. The end goal is to use this method to estimate and improve readability and clarity of administrative or bureaucratic texts. Our toolset is available as a libre software on https://github.com/ufal/Glitter.
title Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts
topic Computation and Language
url https://arxiv.org/abs/2601.05411