Nejla Kalajdžisalihović · ExELL · 2026
The paper explores a more comprehensive approach to assessing text-level difficulty by combining quantitative readability metrics with qualitative analyses of content and context which help in reading comprehension and reading-for-translation. It compares two excerpts using eight readability scores formulas (Automated Readability Index, Flesch Reading Ease, Gunning Fog Index, Flesch-Kincaid Grade Level, Coleman-Liau Readability Index, Smog Index, Original Linsear Write Formula, Linsear Write Grade Level Formula) to explore how topic, content, and context may be used as indicators of text-level difficulty. Using authentic texts, specifically interviews from Humans of New York, the paper aims to demonstrate that other (extra)linguistic features must be considered beyond the numerical scores provided by readability formulas.
Cited by 0Open access
Khan, Fatimah Lyba · 2025
This thesis investigates the use of Large Language Models (LLMs) for scientific text simplification, aiming to enhance accessibility across various educational levels while maintaining scientific accuracy. It addresses the challenge of simplifying complex scientific texts for a wide audience, including students, professionals, and the general public. A key component is the development of SciGrade, a multigrade dataset with simplified versions of scientific texts spanning 10 Science fields. This dataset serves as a benchmark for evaluating the performance of small and medium-scale LLMs in the simplification task. The thesis employs a multi-step evaluation framework, combining automated metrics (e.g., SARI, BERTScore, FKGL, FRE), LLM-based assessments, and human annotations. Larger models like Mistral-24B and Qwen-14B excel in similarity, accuracy, and readability. Self-reflection improves coherence and precision, offering scalable solutions for scientific communication. This work contributes to the advancement of AI-driven text simplification, with im plications for education, crossdisciplinary research, and public science communication, facilitating wider access to scientific knowledge across diverse audiences.
Cited by 0Open access
Sowmya Vajjala, Ivana Lučić · 2018
This paper describes the collection and compilation of the OneStopEnglish corpus of texts written at three reading levels, and demonstrates its usefulness for through two applications -automatic readability assessment and automatic text simplification. The corpus consists of 189 texts, each in three versions (567 in total). The corpus is now freely available under a CC by-SA 4.0 license 1 and we hope that it would foster further research on the topics of readability assessment and text simplification.
Cited by 106Open access
Alessia Battisti, Sarah Ebling · arXiv (Cornell University) · 2019
In this paper, we present a corpus for use in automatic readability\nassessment and automatic text simplification of German. The corpus is compiled\nfrom web sources and consists of approximately 211,000 sentences. As a novel\ncontribution, it contains information on text structure, typography, and\nimages, which can be exploited as part of machine learning approaches to\nreadability assessment and text simplification. The focus of this publication\nis on representing such information as an extension to an existing corpus\nstandard.\n
Cited by 9Open access
2022
Cited by 1Open access
Rémi Cardon, A. Seza Doğruöz · ArXiv.org · 2025
Readability is a key concept in the current era of abundant written information. To help making texts more readable and make information more accessible to everyone, a line of researched aims at making texts accessible for their target audience: automatic text simplification (ATS). Lately, there have been studies on the correlations between automatic evaluation metrics in ATS and human judgment. However, the correlations between those two aspects and commonly available readability measures (such as readability formulas or linguistic features) have not been the focus of as much attention. In this work, we investigate the place of readability measures in ATS by complementing the existing studies on evaluation metrics and human judgment, on English. We first discuss the relationship between ATS and research in readability, then we report a study on correlations between readability measures and human judgment, and between readability measures and ATS evaluation metrics. We identify that in general, readability measures do not correlate well with automatic metrics and human judgment. We argue that as the three different angles from which simplification can be assessed tend to exhibit rather low correlations with one another, there is a need for a clear definition of the construct in ATS.
Cited by 0Open access
2024
Cited by 0Open access
2025
Cited by 0Open access
Martina Miliani, Marco S. G. Senaldi, Gianluca E. Lebani et al. · ARCA (Università Ca' Foscari Venezia) · 2022
The complexity of administrative texts can preclude citizens with language disparities from accessing relevant information. Recent deep-learning models of readability assessment and text simplification would greatly benefit from training materials that are annotated with the specific needs of the target readers. The aim of the present work is to investigate how differently second language learners of Italian and elderly Italian native speakers read and comprehend administrative texts of different readability levels in digital format, as compared to a control group of Italian native speakers. To this end, we conducted a study where 86 participants from the three groups were asked to perform a comprehension task via smartphone. Participants read administrative texts in their original and simplified form, where simplification was performed on the basis of linguistic features that previous literature considered typical of the administrative domain. Although the applied simplification did not seem to affect text comprehension, we observed differences across the three subject groups, especially in relation to participants’ background.
Cited by 0
Hieronymus Hansen, Adam Widera, Johannes Ponge et al. · Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences · 2021
In times of social media, crisis managers can interact with the citizens in a variety of ways. Since machine learning has already been used to classify messages from the population, the question is, whether such technologies can play a role in the creation of messages from crisis managers to the population. This paper focuses on an explorative research revolving around selected machine learning solutions for crisis communication. We present systematic literature reviews of readability assessment and text simplification. Our research suggests that readability assessment has the potential for an effective use in crisis communication, but there is a lack of sufficient training data. This also applies to text simplification, where an exact assessment is only partly possible due to unreliable or non-existent training data and validation measures.
Cited by 6Open access
Lorenzo Jaime Yu Flores, Heyuan Huang, Kejian Shi et al. · 2023
Text simplification has emerged as an increasingly useful application of AI for bridging the communication gap in specialized fields such as medicine, where the lexicon is often dominated by technical jargon and complex constructs. Despite notable progress, methods in medical simplification sometimes result in the generated text having lower quality and diversity. In this work, we explore ways to further improve the readability of text simplification in the medical domain. We propose (1) a new unlikelihood loss that encourages generation of simpler terms and (2) a reranked beam search decoding method that optimizes for simplicity, which achieve better performance on readability metrics on three datasets. This study's findings offer promising avenues for improving text simplification in the medical field.
Cited by 7Open access
Karl Swanson (3580583), Shuhan He (275821), Josh Calvano (18387883) et al. · Figshare · 2024
<p>Readability score benchmark of the pre- and post-hypernym substituted text using the T5 approach for text simplification.</p>
Cited by 0Open access
Santosh Maharjan, Arun Shrestha · 2025
Cited by 0Open access
Association for Computational Linguistics 2025, Maharjan, Sujal, Shrestha, Astha · Underline Science Inc. · 2025
This paper describes our submissions to the TSAR 2025 Shared Task on Readability-Controlled Text Simplification. We present a comparative study of three architectures: a minimal rule-based baseline, an expert-enhanced system, and a multi-stage generative pipeline using a T5 model in a zero-shot setting. Because per-instance official scores were not available at the time of analysis, we perform a principled sensitivity analysis via simulated paired bootstrap to assess robustness of our comparative claims. Under a wide range of reasonable assumptions the simpler, more constrained systems show substantially better automatic scores for semantic fidelity and the composite AUTORANK metric. We include diagnostic failure analysis grounded in actual system outputs, discuss limitations of embedding-based guardrails, and provide concise reproducibility notes in the Appendix. Full code, experimental configurations, and outputs will be released upon acceptance to ensure complete reproducibility.
Cited by 0Open access
Karl Swanson (3580583), Shuhan He (275821), Josh Calvano (18387883) et al. · Figshare · 2024
<p>Readability score benchmark of the pre- and post-hypernym substituted text using the Programmatic+AI approach for text simplification.</p>
Cited by 0Open access
Karl Swanson (3580583), Shuhan He (275821), Josh Calvano (18387883) et al. · Figshare · 2024
<p>Readability score benchmark of the pre- and post-hypernym substituted text using the GPT-J-6B approach for text simplification.</p>
Cited by 0Open access
Hayakawa, Akio, Khallaf, Nouran, Sharoff, Serge et al. · Zenodo (CERN European Organization for Nuclear Research) · 2025
Abstract The TSAR 2025 Shared Task on ReadabilityControlled Text Simplification focuses on simplifying English paragraphs written at an advanced level (B2 or higher) and rewriting them to target CEFR levels (A2 or B1). The challenge is to reduce linguistic complexity without sacrificing coherence or meaning. We developed three complementary approaches based on large language models (LLMs). The first approach (Run 1) generates a diverse set of paragraph-level simplifications. It then applies filters to enforce CEFR alignment, preserve meaning, and encourage diversity, and finally selects the candidates with the lowest perceived risk. The second (Run 2) performs simplification at the sentence level, combining structured prompting, coreference resolution, and explainable AI techniques to highlight influential phrases, with candidate selection guidedby automatic and LLM-based judges. The third hybrid approach (Run 3) integrates both strategies by pooling paragraph- and sentencelevel simplifications, and subsequently applying the identical filtering and selection architecture used in Run 1. In the official TSAR evaluation, the hybrid system ranked 2nd overall, while its component systems also achieved competitive results
Cited by 0Open access
Hayakawa, Akio, Khallaf, Nouran, Sharoff, Serge et al. · Zenodo (CERN European Organization for Nuclear Research) · 2025
Abstract The TSAR 2025 Shared Task on ReadabilityControlled Text Simplification focuses on simplifying English paragraphs written at an advanced level (B2 or higher) and rewriting them to target CEFR levels (A2 or B1). The challenge is to reduce linguistic complexity without sacrificing coherence or meaning. We developed three complementary approaches based on large language models (LLMs). The first approach (Run 1) generates a diverse set of paragraph-level simplifications. It then applies filters to enforce CEFR alignment, preserve meaning, and encourage diversity, and finally selects the candidates with the lowest perceived risk. The second (Run 2) performs simplification at the sentence level, combining structured prompting, coreference resolution, and explainable AI techniques to highlight influential phrases, with candidate selection guidedby automatic and LLM-based judges. The third hybrid approach (Run 3) integrates both strategies by pooling paragraph- and sentencelevel simplifications, and subsequently applying the identical filtering and selection architecture used in Run 1. In the official TSAR evaluation, the hybrid system ranked 2nd overall, while its component systems also achieved competitive results
Cited by 0Open access
Akio Hayakawa, Nouran Khallaf, Horacio Saggion et al. · 2025
Cited by 0
José Frederico Rodrigues, Henrique Lopes Cardoso, Carla Teixeira Lopes · 2025
Text simplification converts complex text into simpler language, improving readability and comprehension. This study evaluates the effectiveness of open-source large language models for text simplification across various categories. We created a dataset of 66,620 lead section pairs from English and Simple English Wikipedia, spanning nine categories, and tested Llama 3 for text simplification. We assessed its output for readability, simplicity, and meaning preservation. Results show improved readability, with simplification varying by category. Texts on Time were the most shortened, while Leisure-related texts had the greatest reduction of words/characters and syllables per sentence. Meaning preservation was most effective for the Objects and Education categories.
Cited by 1Open access