Reading comprehension tests are used in a variety of applications, reaching from education to assessing the comprehensibility simplified texts. However, creating such manually and ensuring their quality is difficult time-consuming. In this paper, we explore how large language models (LLMs) can be generate evaluate multiple-choice reading items. To end, compiled dataset German items developed new protocol for human automatic evaluation, including metric call text informativity, which based on...

The article at hand aggregates the work of our group in automatic processing simplified German. We present four parallel (standard/simplified German) corpora compiled and curated by group. report on creation a gold standard sentence alignments from sources for evaluating alignment methods this standard. show that one performs best majority data sources. used two as basis first sentence-based neural machine translation (NMT) approach toward simplification In follow-up work, we extended model...

The task of document-level text simplification is very similar to summarization with the additional difficulty reducing complexity. We introduce a newly collected data set German texts, from Swiss news magazine 20 Minuten (‘20 Minutes’) that consists full articles paired simplified summaries. Furthermore, we present experiments on automatic pretrained multilingual mBART and modified version thereof more memory-friendly, using both our new existing corpora. Our modifications let us train at...

Text simplification refers to the process of increasing comprehensibility texts. Automatic text models are most commonly evaluated by experts or crowdworkers instead primary target groups simplified texts, such as persons with intellectual disabilities. We conducted an evaluation study including participants and without disabilities reading unsimplified, automatically manually German texts on a tablet computer. explored four different approaches measuring comprehensibility: multiple-choice...

Text simplification refers to the process of increasing comprehensibility texts. Automatic text models are most commonly evaluated by experts or crowdworkers instead primary target groups simplified texts, such as persons with intellectual disabilities. We conducted an evaluation study including participants and without disabilities reading unsimplified, automatically manually German texts on a tablet computer. explored four different approaches measuring comprehensibility: multiple-choice...

In research on Easy Language and automatic text simplification, it is imperative to evaluate the comprehensibility of texts by presenting them target users assessing their level comprehension. Target readers often include people with intellectual or other disabilities, which renders conducting experiments more challenging time-consuming. this paper, we introduce Okra , an openly available touchscreen-based application facilitate inclusion disabilities in studies comprehensibility. It...

Measuring text comprehension is crucial for evaluating the accessibility of texts in Easy Language. However, accurate and objective tests tend to be expensive, time-consuming sometimes difficult implement target groups In this paper, we propose using computer-based testing with touchscreen devices as a means simplify accelerate data collection tests, facilitate experiments less proficient readers. We demonstrate by designing implementing mobile application validating its effectiveness an...

The task of document-level text simplification is very similar to summarization with the additional difficulty reducing complexity. We introduce a newly collected data set German texts, from Swiss news magazine 20 Minuten (‘20 Minutes’) that consists full articles paired simplified summaries. Furthermore, we present experiments on automatic pretrained multilingual mBART and modified version thereof more memory-friendly, using both our new existing corpora. Our modifications let us train at...

Eye movements are known to reflect cognitive processes in reading, and psychological reading research has shown that eye gaze patterns differ between readers with without dyslexia. In recent years, researchers have attempted classify dyslexia based on their using Support Vector Machines (SVMs). However, these approaches (i) highly aggregated features averaged over all words read by a participant, thus disregarding the sequential nature of movements, (ii) do not consider linguistic stimulus...

Eye movements are known to reflect cognitive processes in reading, and psychological reading research has shown that eye gaze patterns differ between readers with without dyslexia. In recent years, researchers have attempted classify dyslexia based on their using Support Vector Machines (SVMs). However, these approaches (i) highly aggregated features averaged over all words read by a participant, thus disregarding the sequential nature of movements, (ii) do not consider linguistic stimulus...