Millions of people worldwide face barriers in accessing and understanding complex written information due to limited literacy. Automatic text simplification (ATS) addresses this challenge by transforming complex texts into simpler, more accessible versions. However, most existing ATS research focuses on English, leaving Spanish, a language spoken by over 500 million people, underrepresented. This paper fills this gap by introducing large-scale sentence-aligned simplification resources for Spanish, developed from the Newsela and ClearSim corpora. We propose detailed guidelines for manual alignment, evaluate a wide range of automatic sentence alignment algorithms, and present the first systematic exploration of LLM-based monolingual sentence alignment in Spanish. Our analysis incorporates comprehensive quantitative and qualitative evaluation, supported by statistical significance testing, and reveals clear differences in the structural simplification patterns across corpora. In addition, we train and release baseline ATS models using the new aligned datasets, demonstrating their practical utility for downstream simplification. All alignment code, trained models, and evaluation scripts will be publicly released to ensure transparency and reproducibility. Together, these contributions substantially advance the resources and methodology for Spanish-language ATS.

Abstract The simplification of language – particularly with regard to administrative discourse – has long been a central concern within Italian linguistics. Over the past few decades, significant progress has been made, including the development of consolidated and widely accepted lists of linguistic features – both morphosyntactic and lexical – that influence textual simplicity and accessibility (cf. Fiorentino/Ganfi 2024). These advances contributed to the early creation of a readability index, the Gulpease index , in the 1980 s (cf. Lucisano/Piemontese 1988). Within this framework, the authors have developed a software for the automatic simplification of administrative texts, supported by QWEN3 (a large language model, LLM), entitled SEMPL-IT (cf. Russodivito et al. 2024; Fiorentino/Russodivito 2025; Ganfi/Russodivito 2025; Fiorentino et al. forthcoming; Fiorentino/Russodivito forthcoming). As part of this project, a corpus named ItaIst (Fiorentino et al. 2024b) The ItaIst corpus is publicly available on Hugging Face at the following link: https://huggingface.co/datasets/VerbACxSS/ItaIst (15 July 2025). was compiled and subjected to automatic simplification using the BASIC approach , resulting in a parallel corpus of simplified texts. This simplified corpus was then compared to the source corpus and evaluated in terms of improved readability and Semantic similarity (cf. Chandrasekaran et al. 2021), with the objective of validating the effectiveness of the simplification process. In this contribution, we introduce and validate a new methodology – the CHAIN approach – applied to a different corpus, ItaRegol (Fiorentino et al. 2024a). The ItaRegol corpus is publicly available on Hugging Face at the following link: https://huggingface.co/datasets/VerbACxSS/ItaRegol (15 July 2025). Although smaller in size than ItaIst , ItaRegol comprises rules and regulations, i. e., legally binding texts that create, modify, or extinguish subjective legal positions. Due to the legal nature of these texts, simplification must be carried out with caution to avoid altering their legal effects. This paper compares the two simplification approaches – BASIC and CHAIN – by evaluating the parameters adopted, assessing the quality of the simplified output, and drawing conclusions regarding the differing impact of these strategies in enhancing the readability of administrative versus regulatory texts.

The article examines an approach to modular modelling of architectural objects aimed at producing photorealistic three-dimensional cartographic representations of urban areas. The study is based on an analysis of contemporary methods for constructing building models-plan extrusion, photogrammetric reconstruction, and manual modelling — and identifies their limitations under real-time visualisation. It is noted that automatic simplification of monolithic models leads to loss of semantic and visual façade characteristics, especially at medium viewing distances where recognisability of architectural forms and proportions must be preserved. As an alternative, the concept is proposed of representing buildings as assemblies of repeating façade modules with standardised connection interfaces, parametric compatibility, and the possibility of repeated use when creating new objects. Using the façade of the university’s main building as a test case, an approbation was carried out that included the identification of typical elements through intelligent image segmentation algorithms and the subsequent formation of a modular structure. The results show that up to eighty percent of the façade surface can be reconstructed from repeating elements while preserving visual plausibility. Data from laser scanning were used for metric calibration of model elements. The research confirms the applicability of the modular approach for optimising three-dimensional cartography, simplifying model updates, and integrating into digital twins of urban areas, demonstrating potential for visual navigation, virtual excursions, and analysis of the urban built environment, while combining photorealism, technological rationality, and reproducibility.

This research presents a multi-stage heuristic pipeline to refine the Spanish Boletín Oficial del Estado (BOE) corpus for Natural Language Processing tasks. Raw legal corpora are often filled with noise, including OCR errors, lists, tables, and non-textual placeholders, making them unsuitable for training language models. Our methodology first normalizes the text by correcting character-level errors and repairing hyphenation. Subsequently, it applies a series of filters based on quantifiable metrics, such as newline character ratios, non-alphabetic character counts, and misspelled word percentages, to detect and discard structurally and semantically unsuitable segments. A key contribution is the novel Combined Borderline Score (CBS), which identifies and removes marginal segments that are close to multiple failure thresholds. The result is a significantly cleaner corpus of legal texts, providing a high-quality foundation for training models for tasks like automatic text simplification and offering a reusable methodology for cleaning other large and diverse legal texts.

This research aims to describe the performance of ChatGPT-3.5 and ChatGPT-4o in the task of Automatic Text Simplification (ATS) in Italian institutional texts. The aim is to analyse the linguistic differences between the original texts compared to their simplified rewritings by ChatGPT, and the impact of these differences on non-expert users’ experience. A dataset of six short texts was compiled to be rewritten using a zero-shot instructional prompt. The methodological approach combined quantitative linguistic analyses, manual analysis and human judgment to assess the effectiveness of the simplification. For the quantitative linguistic analysis, an additional comparison was made between ChatGPT’s rewritings and human revisions, used as an external benchmark to better contextualize the AI’s simplification strategies. The study provides new insights into the linguistic structure of administrative-bureaucratic texts by examining readability parameters and collecting subjective assessments of comprehension and perceived comprehensibility. It also aims to contribute to the growing body of research on text simplification methods and the role of large language models (LLMs) in enhancing accessibility to complex institutional discourse.

By reducing the number of lines of code, program simplification reduces code complexity, improving software maintainability and code comprehension. While several existing techniques can be used for automatic program simplification, there is no consensus on the effectiveness of these approaches. We present the first study on how real-world developers simplify programs in open-source software projects. By analyzing 382 pull requests from 296 projects, we summarize the types of program transformations used, the motivations behind simplifications, and the set of program transformations that have not been covered by existing refactoring types. As a result of our study, we submitted eight bug reports to a widely used refactoring detection tool, RefactoringMiner, where seven were fixed. Our study also identifies gaps in applying existing approaches for automating program simplification and outlines the criteria for designing automatic program simplification techniques. In light of these observations, we propose SimpT5, a tool to automatically produce simplified programs that are semantically equivalent programs with reduced lines of code. SimpT5 is trained on our collected dataset of 92,485 simplified programs with two heuristics: (1) modified line localization that encodes lines changed in simplified programs, and (2) checkers that measure the quality of generated programs. Experimental results show that SimpT5 outperforms prior approaches in automating developer-induced program simplification.

Ensuring the ACID properties of transactions is the fundamental functionality of transactional DBMSs. However, through our study on existing solutions on transaction management, we found that transaction implementations in some mainstream databases, such as MySQL, MariaDB and TiDB, may violate what they claim in their documentation, in the form of incorrect database state or query results. Since there is still a lack of efficient and comprehensive testing methods to detect bugs within transaction management implementation for off-the-shelf DBMSs at present, we propose Fucci, a fuzzing framework, to solve the problem. Given a target DBMS, Fucci improves the efficiency of detecting transaction bugs through three key components: Random Conflict Construction (RCC), Multilevel Constraint Solving (MCS), and Experience-driven Automatic Simplification (EAS). RCC addresses the issue of inadequate case validity by ensuring the presence of read-write or write-write conflicts between transactions. MCS enhances the accuracy and efficiency of the transaction oracle by employing an external multi-version control system to solve data visibility. EAS is ultimately adopted to improve the efficiency of simplification and the readability of the identified bug cases. All of the above strategies are tested on commercial databases such as MySQL, MariaDB and TiDB. Accordingly, 6 previously unknown transaction bugs and 14 known duplicate transaction bugs have been newly discovered, most of which have been officially acknowledged.

In this study, we present the results of experiments on text simplification for the Lithuanian language, where we aim to simplify administrative-style texts to the Plain Language level. We selected mT5, mBART, and LT-Llama-2 as the foundational models and fine-tuned them for the text simplification task. Additionally, we evaluated ChatGPT for this purpose. Also, we conducted a comprehensive assessment of the simplification results provided by these models both quantitatively and qualitatively. The results demonstrated that mBART was the most effective model for simplifying Lithuanian administrative text, achieving the highest scores across all the evaluation metrics. A qualitative evaluation of the simplified sentences complemented our quantitative findings. Attention analysis provided insights into model decisions, highlighting strengths in lexical and syntactic simplifications but revealing challenges with longer, complex sentences. Our findings contribute to advancing text simplification for lesser-resourced languages, with practical applications for more effective communication between institutions and the general public, which is the goal of Plain Language.

Access to information is a fundamental human right that contributes to freedom of expression and self-determination. However, information availability alone is not enough: the way in which information is expressed and presented on paper or in digital format can be extremely complicated to understand and act upon for a highly diverse set of people with varying ranges of reading, writing and understanding abilities. For a long time, artificial intelligence (AI) and natural language processing (NLP) have dedicated research efforts in the field of automatic text simplification to the development of methods to automate the production of easy-to-read texts. However, in spite of AI hype, the problem persists. Current NLP models such as large language models (LLMs) are still not well understood, and their use in the development of text simplification needs careful assessment. In this paper, having identified the need for easy-to-read, accessible texts, we provide a light overview of current methods in NLP and provide a lay explanation of several techniques applied to lexically and syntactically modified texts to make them simpler to read and understand. We conclude by raising awareness on the use of general tools to address this very challenging problem that can affect contemporary lives.

ABSTRACTThe smooth polyhedral model has been commonly used to construct non‐spherical particles with smooth surfaces, whereas it is mainly constrained to numerical simulations involving concave‐shaped particles. This constraint arises from the limitations imposed by the contact algorithm. In this study, the contact detection between smooth polyhedrons is simplified to that between dilated triangular elements, and a discrete element method for concave polyhedral particles with smooth surfaces is developed. Subsequently, an automatic mesh simplification algorithm is established to enhance the computational efficiency without compromising accuracy. In validating the smooth polyhedral model, the simulation results of a hexahedron colliding with a plane are found to agree favorably with the experimental results. Then, the elastic collisions between the convex and concave particles are analyzed, and the total kinetic energy before and after the particle collision remains unchanged. Furthermore, the influences of particle morphology on the packing fraction, flow fluctuation, flow rate, mixing rate, velocity distribution, and system energy in hoppers and rotating drums are analyzed, revealing the underlying flow characteristics of concave polyhedral granular materials with smooth surfaces.

Automatic text simplification models face the challenge of generating outputs that, while being indeed simpler, still retain some complexity. This stems from the inherently relative nature of simplification, wherein a given text is transformed into a relatively simpler version, which does not necessarily equate to simple. We thus aim to propose a finer-grained method to assess sentence complexity in French. Our solution comprises three models, in which two address absolute and relative sentence complexity assessment, while the third focuses on measuring simplicity gain. By employing this triad of models, we aim to offer a comprehensive approach to qualify and quantify sentence simplicity. Our approach utilizes FlauBERT, fine-tuned for classification and regression tasks. Based on our three-dimensional complexity analysis, we provide the WiViCo dataset, comprising 46,525 aligned complex-simpler pairs, which is further leveraged to fine-tune different FLAN-T5-based language models for simplified text generation. In this context, we perform different evaluation tasks that contrast human evaluations with BLEU and SARI metrics for the generated simplifications, the models’ computational efficiency and environmental impact.

Text simplification reduces the complexity of text while preserving essential information, thus making it more accessible to a broad range of readers, including individuals with cognitive disorders, non-native speakers, children, and the general public. In this paper, we present experiments on text simplification for the Lithuanian language, aiming to simplify administrative texts to a Plain Language level. We fine-tuned mT5 and mBART models for this task and evaluated the effectiveness of ChatGPT as well. We assessed simplification results via both quantitative metrics and qualitative evaluation. Our findings indicated that mBART performed the best as it achieved the best scores across all evaluation metrics. The qualitative analysis further supported these findings. ChatGPT experiments showed that it responded quite well to a short and simple prompt to simplify the given text; however, it ignored most of the rules given in a more elaborate prompt. Finally, our analysis revealed that BERTScore and ROUGE aligned moderately well with human evaluations, while BLEU and readability scores indicated lower or even negative correlations

The simplification of complex networks is a research field closely related to graph theory in discrete mathematics. The existing methods are typically limited to simplifying the series sub-networks, parallel sub-networks, diagonal sub-networks, and nested simple sub-networks. From the current perspective, there are no available methods that can handle complex sub-networks and nested complex sub-networks. In this paper, we innovatively propose an efficient and automatic equivalence simplification method for arbitrary complex ventilation networks. The method enables, for the first time, the maximum possible equivalence simplification of nested simple sub-networks and nested complex sub-networks. In order to avoid the NP-hard problem caused by the searching of simplifiable sub-networks, it is necessary to analyze the intrinsic topology relationship between simplifiable sub-networks and spanning sub-graphs to optimize the searching process. One of our main contributions is that we present an efficient searching method for arbitrarily nested reducible sub-networks based on the bidirectional traversal process of a directed tree. The method optimizes the searching process for simplifiable node pairs by combining the characteristics of a directed tree with the judgment rules of simplifiable sub-networks. Moreover, by deriving the formula of an equivalent air resistance calculation for complex sub-networks, another one of our main contributions is that we present an equivalent calculation and simplification method for arbitrarily complex sub-networks based on the principle of energy conservation. The basic idea of the method is to calculate the equivalent air resistance using the ventilation network resolution of the constructed virtual sub-networks. We realize the simplification method of arbitrarily complex mine ventilation networks, and we validate the reliability of the simplification method by comparing the air distribution results using the network solution method before and after simplification. It can be determined that, with appropriate modifications to meet specific requirements, the proposed method can also be applicable to equivalent simplification instances of other types of complex networks. Based on the results analysis of several real-world mine ventilation network examples, the effectiveness of the proposed method is further verified, which can satisfactorily meet the requirements for simplifying complex networks.

An adaptive stratification algorithm based on gradient fitting deviation and its application to acoustic ray-tracing algorithm

Abstract Automatic text simplification (TS) aims to automate the process of rewriting text to make it easier for people to read. A pre-requisite for TS to be useful is that it should convey information that is consistent with the meaning of the original text. However, current TS evaluation protocols assess system outputs for simplicity and meaning preservation without regard for the document context in which output sentences occur and for how people understand them. In this work, we introduce a human evaluation framework to assess whether simplified texts preserve meaning using reading comprehension questions. With this framework, we conduct a thorough human evaluation of texts by humans and by nine automatic systems. Supervised systems that leverage pre-training knowledge achieve the highest scores on the reading comprehension tasks among the automatic controllable TS systems. However, even the best-performing supervised system struggles with at least 14% of the questions, marking them as “unanswerable” based on simplified content. We further investigate how existing TS evaluation metrics and automatic question-answering systems approximate the human judgments we obtained.

The task of Automatic Text Simplification (ATS) aims to transform texts to improve their readability and comprehensibility. Current solutions are based on Large Language Models (LLM). These models have high performance but require powerful computing resources and large amounts of data to be fine-tuned when working in specific and technical domains. This prevents most researchers from adapting the models to their area of study. The main contributions of this research are as follows: (1) proposing an accurate solution when powerful resources are not available, using the transfer learning capabilities across different domains with a set of linguistic features using a reduced size pre-trained language model (T5-small) and making it accessible to a broader range of researchers and individuals; (2) the evaluation of our model on two well-known datasets, Turkcorpus and ASSET, and the analysis of the influence of control tokens on the SimpleText corpus, focusing on the domains of Computer Science and Medicine. Finally, a detailed discussion comparing our approach with state-of-the-art models for sentence simplification is included.

Being able to read and understand written text is critical in a digital era. However, studies shows that a large fraction of the population experiences comprehension issues. In this context, further initiatives in accessibility are required to improve the audience text comprehension. However, writers are hardly assisted nor encouraged to produce easy-to-understand content. Moreover, Automatic Text Simplification (ATS) model development suffers from the lack of metric to accurately estimate comprehension difficulty We present LC-SCORE, a simple approach for training text comprehension metric for any French text without reference i.e. predicting how easy to understand a given text is on a [0,100] scale. Our objective with this scale is to quantitatively capture the extend to which a text suits to the Langage Clair (LC, Clear Language) guidelines, a French initiative closely related to English Plain Language. We explore two approaches: (i) using linguistically motivated indicators used to train statistical models, and (ii) neural learning directly from text leveraging pre-trained language models. We introduce a simple proxy task for comprehension difficulty training as a classification task. To evaluate our models, we run two distinct human annotation experiments, and find that both approaches (indicator based and neural) outperforms commonly used readability and comprehension metrics such as FKGL and SAMSA.

ABSTRACT Polyline simplification is crucial for cartography and spatial database management. In recent decades, various rule-based algorithms for vector polyline simplification have been proposed. However, most existing algorithms lack parameter self-adaptive capabilities and require repeated manual parameter adjustments when applied to different polylines. While deep-learning-based methods have recently been introduced for raster polyline image simplification, they cannot achieve end-to-end simplification when the input data and output results are vector polylines. This paper proposes a new deep-learning-based method for vector polyline simplification by integrating both the vector and raster features of the polyline. Specifically, a deep separable convolutional residual neural network was first used to extract the convolutional features of each image. Then, the region proposal network was modified to generate proposal boxes using vector coordinates, and these proposal boxes were used to locate the convolutional feature maps of bends. Finally, convolutional feature maps were fed into a binary classification network to identify unimportant vertices that should be omitted for vector polyline simplification. The experimental results indicated that the proposed method can exploit raster and vector features to achieve automatic and effective polyline simplification without prior map generalization knowledge and manual settings of rules and parameters. The polyline simplification results of the proposed method have a higher compression ratio of coordinate points and lower shape deformation and deviation than the results generated by the classic Wang and Müller (WM) algorithm and Support Vector Machine (SVM) based algorithm, which shows the potential of the proposed method for future applications in map generalization.

In the field of automatic text simplification, assessing whether or not the meaning of the original text has been preserved during simplification is of paramount importance. Metrics relying on n-gram overlap assessment may struggle to deal with simplifications which replace complex phrases with their simpler paraphrases. Current evaluation metrics for meaning preservation based on large language models (LLMs), such as BertScore in machine translation or QuestEval in summarization, have been proposed. However, none has a strong correlation with human judgment of meaning preservation. Moreover, such metrics have not been assessed in the context of text simplification research. In this study, we present a meta-evaluation of several metrics we apply to measure content similarity in text simplification. We also show that the metrics are unable to pass two trivial, inexpensive content preservation tests. Another contribution of this study is MeaningBERT (https://github.com/GRAAL-Research/MeaningBERT), a new trainable metric designed to assess meaning preservation between two sentences in text simplification, showing how it correlates with human judgment. To demonstrate its quality and versatility, we will also present a compilation of datasets used to assess meaning preservation and benchmark our study against a large selection of popular metrics.

In research on Easy Language and automatic text simplification, it is imperative to evaluate the comprehensibility of texts by presenting them to target users and assessing their level of comprehension. Target readers often include people with intellectual or other disabilities, which renders conducting experiments more challenging and time-consuming. In this paper, we introduce Okra, an openly available touchscreen-based application to facilitate the inclusion of people with disabilities in studies of text comprehensibility. It implements several tasks related to reading comprehension and cognition and its user interface is optimized toward the needs of people with intellectual disabilities (IDs). We used Okra in a study with 16 participants with IDs and tested for effects of modality, comparing reading comprehension results when texts are read on paper and on an iPad. We found no evidence of such an effect on multiple-choice comprehension questions and perceived difficulty ratings, but reading time was significantly longer on paper. We also tested the feasibility of assessing cognitive skill levels of participants in Okra, and discuss problems and possible improvements. We will continue development of the application and use it for evaluating automatic text simplification systems in the future.