Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts
This work addresses readability and clarity issues for users of administrative or bureaucratic texts, presenting an incremental tool for visualization.
The paper tackles the problem of estimating readability in administrative texts by measuring information entropy, proposing a visualization framework that uses multiple language models to approximate entropy and visualize results, with the toolset made available as libre software.
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.