Ensuring accessibility for individuals with cognitive impairments is essential for autonomy, self-determination, and full citizenship. However, manual Easy-to-Read (ETR) text adaptations are slow, costly, and difficult to scale, limiting access to crucial information in healthcare, education, and civic life. AI-driven ETR generation offers a scalable solution but faces key challenges, including dataset scarcity, domain adaptation, and balancing lightweight learning of Large Language Models (LLMs). In this paper, we introduce ETR-fr, the first dataset for ETR text generation fully compliant with European ETR guidelines. We implement parameter-efficient fine-tuning on PLMs and LLMs to establish generative baselines. To ensure high-quality and accessible outputs, we introduce an evaluation framework based on automatic metrics supplemented by human assessments. The latter is conducted using a 36-question evaluation form that is aligned with the guidelines. Overall results show that PLMs perform comparably to LLMs and adapt effectively to out-of-domain texts. Code and datasets are available at https://github.com/FrLdy/ETR-fr.

Simplifying complex texts is essential to ensure equitable access to information, particularly for individuals with cognitive impairments.The Easy-to-Read (ETR) initiative provides a framework to make content more accessible for these individuals.However, manually creating such texts remains time-consuming and resourceintensive.In this work, we investigate the potential of large language models (LLMs) to automate the generation of ETR content.To address the scarcity of aligned corpora and the specific constraints of ETR, we propose a multitask learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation.We explore two complementary strategies: multi-task retrievalaugmented generation (RAG) for in-context learning (ICL), and MTL-LoRA for parameterefficient fine-tuning (PEFT).Our experiments with Mistral-7B and LLaMA-3-8B, conducted on ETR-fr, a new high-quality dataset, show that MTL-LoRA consistently outperforms all other strategies in in-domain settings, while the MTL-RAG-based approach achieves better generalization in out-of-domain scenarios.

As Picasso said, a painting lives only through the one who looks at it. To materialize this thought, we propose to automatically produce artworks that visually transform paintings by amplifying and distorting the most observed areas by viewers. Our work is based on a study conducted at the Caen Museum of Fine Arts in France. During the study, 151 participants were equipped with eye-tracking glasses, and observed various paintings, first alone and then in pairs. Based on the fixation and gaze path stored data, we first generate saliency maps that reflect the visual attention given to each painting. These maps are then used to fine-tune the UNETRSal model, a neural network designed to predict saliency maps, in order to align its outputs with human visual patterns observed during the experiment. The saliency maps generated are subsequently used to create deformations of the original painting. This overall process gives rise to a new artwork born from the interaction between human gaze and AI-prediction.

Tools designed to extract main content from web pages require thorough evaluation, yet existing benchmarks disproportionately focus on English-language datasets. Consequently, previous studies have shown that while these extractors are well-optimized for English, their effectiveness partially or entirely diminishes in other languages. This study reproduces and extends recent benchmarks by incorporating multilingual datasets as a key factor. We analyze extractor performance across five languages-Greek, English, Polish, Russian, and Chinese-highlighting the need to adapt extraction models to linguistic variations. Our results show that while some extractors maintain stable performance, others suffer significant drops in precision and recall on non-English or structurally irregular pages.

Web page segmentation (WPS) aims to break a web page into different segments with coherent intra- and inter-semantics. By evidencing the morpho-dispositional semantics of a web page, WPS has traditionally been used to demarcate informative from non-informative content, but it has also evidenced its key role within the context of non-linear access to web information for visually impaired people. For that purpose, a great deal of ad hoc solutions have been proposed that rely on visual, logical, and/or text cues. However, such methodologies highly depend on manually tuned heuristics and are parameter-dependent. To overcome these drawbacks, principled frameworks have been proposed that provide the theoretical bases to achieve optimal solutions. However, existing methodologies only combine few discriminant features and do not define strategies to automatically select the optimal number of segments. In this article, we present a multi-objective clustering technique called MCS that relies on \( K \) -means, in which (1) visual, logical, and text cues are all combined in a early fusion manner and (2) an evolutionary process automatically discovers the optimal number of clusters (segments) as well as the correct positioning of seeds. As such, our proposal is parameter-free, combines many different modalities, does not depend on manually tuned heuristics, and can be run on any web page without any constraint. An exhaustive evaluation over two different tasks, where (1) the number of segments must be discovered or (2) the number of clusters is fixed with respect to the task at hand, shows that MCS drastically improves over most competitive and up-to-date algorithms for a wide variety of external and internal validation indices. In particular, results clearly evidence the impact of the visual and logical modalities towards segmentation performance.

We present results of an empirical study for examining the performance of sighted and blind individuals in discriminating structures of web pages through vibro-tactile feedbacks.

In this paper, we examine the performance of blind individuals in discriminating ranges of amplitudes through vibro-tactile feedbacks.

Tag thunder is an audio version of a visual tag cloud content representation. Tag thunders aim to bring quick reading strategies, such as skimming, to blind people. Tag thunders vocalize the key terms of a page using concurrent speech paradigm coupled with additional audio effects, similar to visual effects in a tag cloud. In this paper we present our implementation of the tag thunder concept. Our system comprises three modules: page segmentation, key term extraction and tag thunder vocalization. The evaluation results show the viability of the tag thunder concept.

In this paper, we present results of an empirical study for examining the performance of blind individuals in recognizing shapes through a vibro-tactile feedback. The suggested vibro-tactile system maps different shades of grey to one pattern low-frequencies tactical vibrations. Performance data is reported, including number of errors, and qualitative understanding of the displayed shapes.