For the Master’s thesis in Artificial Intelligence, readability assessment for text simplification was investigated, with a focus on the evaluation of linguistic, syntactic, and statistical features for measuring text complexity and supporting effective simplification strategies. Through this work, a solid understanding of NLP pipelines, feature engineering, and evaluation methodologies for language accessibility was developed.
Within the scope of the project, applied NLP techniques were employed to bridge theoretical approaches with real-world applications aimed at improving text comprehension and accessibility. This experience contributed to the development of strong skills in designing data-driven solutions for complex language processing tasks.
Furthermore, experimental analyses were conducted to assess the effectiveness of different readability measures and simplification approaches, with attention to performance evaluation and result interpretation. This process strengthened competencies in empirical analysis, critical evaluation of models, and the translation of research findings into practical insights.