Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts
By: Jan Černý, Ivana Kvapilíková, Silvie Cinková
Potential Business Impact:
Makes confusing writing easier to understand.
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.
Similar Papers
Readability Formulas, Systems and LLMs are Poor Predictors of Reading Ease
Computation and Language
Makes reading easier by watching how people read.
Measuring and Analyzing Intelligence via Contextual Uncertainty in Large Language Models using Information-Theoretic Metrics
Artificial Intelligence
Shows how AI thinks by tracking its guessing.
How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?
Computation and Language
Better reading speed by understanding word difficulty.