Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LLM Agent-Assisted Reverse Engineering with Quantitative Readability Metrics
Automatic decompilers produce functionally correct but often unreadable C code. This paper addresses one stage of the reverse engineering workflow: improving the readability of decompiled code using LLM agents guided by …
Addressing surprisal deficiencies in reading time models
This study demonstrates a weakness in how n-gram and PCFG surprisal are used to predict reading times in eye-tracking data. In particular, the information conveyed by words skipped during saccades is not usually included…
The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgments. However, surprisal is tightly intertwined with lexical frequency. …
AMesure: a readability formula for administrative texts (AMESURE: une plateforme de lisibilit\'e pour les textes administratifs) [in French]
Psycholinguistic Models of Sentence Processing Improve Sentence Readability Ranking
While previous research on readability has typically focused on document-level measures, recent work in areas such as natural language generation has pointed out the need of sentence-level readability measures. Much of p…
Information RetrievalSentenceText GenerationText Simplification