A simplificação de sentenças frequentemente altera a estrutura textual enquanto preserva o significado, tornando a fidelidade semântica difícil de avaliar. Neste trabalho, investigamos se representações baseadas em grafos derivadas de Extração Aberta de Informação (Open IE) podem capturar a preservação semântica em diferentes níveis de simplificação. Utilizando o corpus PorSimplesSent, extraímos triplas relacionais de sentenças originais e simplificadas para construir grafos semânticos comparáveis. Os resultados fornecem indícios exploratórios de que a análise baseada em grafos pode capturar diferenças semânticas relevantes e fornece sinais complementares além da sobreposição lexical superficial para avaliar a qualidade da simplificação.

This paper presents exploratory results from the "Novo CorPop Saúde" project, evaluating whether validation by expert linguists improves readability levels compared to AI-generated simplifications. We analyzed original, AI-generated, and human-validated versions of thirty Patient Information leaflets. Using the Flesch Reading Ease Index, two adapted Dale-Chall metrics, and lexicometric analysis, we assessed automatic simplification against human strategies. Results indicate that while AI improves readability scores primarily through text compression, expert linguists prioritize elaborative strategies, maintaining key terminology while providing didactic explanations to fill semantic gaps. This suggests that human intervention plays a key role in balancing terminological precision with communicative accessibility, a nuance that purely reductive AI strategies might overlook. This study provided evidence on the use of the complex and simplified lexical repertoire of medicine leaflets for the "Novo CorPop Saúde".

A divisão silábica é uma tarefa fundamental em aplicações de processamento de linguagem natural (PLN), especialmente na avaliação de leiturabilidade por meio de métricas como o Índice Flesch. Este artigo apresenta o Vidya Syl, um novo algoritmo de divisão silábica implementado em Java, desenvolvido em conformidade com a seção brasileira do Vocabulário Ortográfico Comum da Língua Portuguesa, denominada VOC. A abordagem metodológica adotada consistiu em incrementar, com regras morfológicas e ortográficas, um algoritmo baseado em regras fonológicas e gráficas, até que se tornasse aderente ao VOC. Os resultados experimentais demonstram melhorias tanto em acurácia quanto em cobertura lexical.

Este estudo teve como objetivo atualizar a lista das 3.000 palavras mais frequentes do português do Brasil com base no CorPop de 2018, formado por textos baseados no letramento médio dos leitores do país. A metodologia de atualização utilizada foi comparar frequências do CorPop original com as de outros dois corpora, um baseado no Carolina da USP e outro na Wikipédia, ampliando a base textual. Como resultado, obteve-se uma renovação de 659 palavras, representando 21,97% das originais. Testes comparativos em diferentes ferramentas de análise textual (NILC Metrix, Vidya Text com CorPop original e Vidya Text com CorPop26) evidenciam a influência da lista de palavras mais frequentes no resultado da fórmula de Dale e Chall de 1995.

This paper analyzes the performance of several terminology extraction methods when confronted with historical specialized texts that do not conform with modern orthographical norms. We tested two extraction methods based on linguistic patterns, four prompt-based generative artificial intelligence (GenAI) models, and one BERT-like model. Some of these models went through fine-tuning for terminology extraction, and one of these is specialized in the extraction of medical terms from documents written in Portuguese. For the GenAI models, we tested four different prompting strategies. As test set, we used chapter fifteen of the second part of the book Aviso ’a Gente do Mar sobre a sua Saude [Advice to Sea People about their Health], originally written in French by G. Mauran at the end of the 18th century, and translated and adapted to Portuguese in 1794. The chapter was annotated with terminology, and the evaluation was conducted independently both in terms of f-measure, as well as in terms of pure precision, to observe if the automatic extraction methods could complement the manual token-based annotation. Results show that using automatic extraction methods to complement the manual annotation can improve coverage, and that individual models do not achieve high extraction quality, but, by combining two or more models, a recall of more than 90% could be achieved in the test data.

While most essential medicines have become widely accessible across all social strata in Brazil due to government initiatives and market shifts, a significant barrier remains: the technical complexity of medication leaflets. This pragmatic and linguistic gap hinders patient comprehension of critical risks and benefits. Thus, adapting these texts into plain language patterns is crucial for patient safety and treatment adherence. Large language models have been increasingly effective as practical solutions for text simplification, an important Natural Language Processing (NLP) task that serves as a basis for several other linguistic and computational tasks. However, the scarcity of annotated datasets remains a bottleneck for rigorous evaluation. To bridge this gap, we propose a streamlined pipeline for generating simplified medical leaflets and introduce an initial benchmark dataset of 30 expertly annotated samples. Our results, supported by semantic and morphosyntactic evaluations, demonstrate that the proposed method produces high-quality, simplified content suitable for health applications.

Document simplification has recently attracted increasing attention due to its broader practical applicability compared to sentence-level simplification. Beyond simplifying individual sentences, this task involves preserving fluency, conciseness, and coherence across the entire text, often incorporating summarization techniques. Despite its importance, research in this area remains largely concentrated on a few languages, particularly English.In this work, we introduce LegalSim-PT, the first large-scale Portuguese dataset for document simplification based on legal texts. To mitigate reliance on manual evaluation, we combined data augmentation strategies with readability, semantic similarity, and diversity metrics to select the most suitable document pairs. We conducted a comprehensive analysis of the resulting dataset, first characterizing its surface features and comparing them with those of existing simplification corpora. Next, we assessed its quality using automatic metrics, linguistic indicators, and human evaluations. Finally, we select representative models as baselines and fine-tune two models on LegalSim-PT, achieving improved performance in document-level simplification.

Sentence simplification (SS) focuses on adapting sentences to enhance their readability and accessibility. While large language models (LLMs) match task-specific baselines in English SS, their performance in Portuguese remains underexplored. This paper presents a comprehensive performance comparison of 26 state-of-the-art LLMs in Portuguese SS, alongside two simplification models trained explicitly for this task and language. They are evaluated under a one-shot setting across scientific, news, and government datasets. We benchmark the models with our newly introduced Gov-Lang-BR corpus (1,703 complex-simple sentence pairs from Brazilian government agencies) and two established datasets: PorSimplesSent and Museum-PT. Our investigation takes advantage of both automatic metrics and large-scale linguistic analysis to examine the transformations achieved by the LLMs. Furthermore, a qualitative assessment of selected generated outputs provides deeper insights into simplification quality. Our findings reveal that while open-source LLMs have achieved impressive results, closed-source LLMs continue to outperform them in Portuguese SS.

Automatic text simplification focuses on transforming texts into a more comprehensible version without sacrificing their precision. However, automatic methods usually require (paired) datasets that can be rather scarce in languages other than English. This paper presents a new approach to automatic sentence simplification that leverages paraphrases, context, and linguistic attributes to overcome the absence of paired texts in Portuguese.We frame the simplification problem as a textual style transfer task and learn a style representation using the sentences around the target sentence in the document and its linguistic attributes. Moreover, unlike most unsupervised approaches that require style-labeled training data, we fine-tune strong pre-trained models using sentence-level paraphrases instead of annotated data. Our experiments show that our model achieves remarkable results, surpassing the current state-of-the-art (BART+ACCESS) while competitively matching a Large Language Model.

This paper presents MedSimples, an authoring tool that combines Natural Language Processing, Corpus Linguistics and Terminology to help writers to convert health-related information into a more accessible version for people with low literacy skills. MedSimples applies parsing methods associated with lexical resources to automatically evaluate a text and present simplification suggestions that are more suitable for the target audience. Using the suggestions provided by the tool, the author can adapt the original text and make it more accessible. The focus of MedSimples lies on texts for special purposes, so that it not only deals with general vocabulary, but also with specialized terms. The tool is currently under development, but an online working prototype exists and can be tested freely. An assessment of MedSimples was carried out aiming at evaluating its current performance with some promising results, especially for informing the future developments that are planned for the tool.

This paper presents a lexical resource developed for Portuguese. The resource contains sentences annotated with semantic roles. The sentences were extracted from two domains: Cardiology research papers and newspaper articles. Both corpora were analyzed with the PALAVRAS parser and subsequently processed with a subcategorization frames extractor, so that each sentence that contained at least one main verb was stored in a database together with its syntactic organization. The annotation was manually carried out by a linguist using an annotation interface. Both the annotated and non-annotated data were exported to an XML format, which is readily available for download. The reason behind exporting non-annotated data is that there is syntactic information collected from the parser annotation in the non-annotated data, and this could be useful for other researchers. The sentences from both corpora were annotated separately, so that it is possible to access sentences either from the Cardiology or from the newspaper corpus. The full resource presents more than seven thousand semantically annotated sentences, containing 192 different verbs and more than 15 thousand individual arguments and adjuncts.

Comparable corpora have been used as an alternative for parallel corpora as resources for computational tasks that involve domain-specific natural language processing. One way to gather documents related to a specific topic of interest is to traverse a portion of the web graph in a targeted way, using focused crawling algorithms. In this paper, we compare several focused crawling algorithms using them to collect comparable corpora on a specific domain. Then, we compare the evaluation of the focused crawling algorithms to the performance of linguistic processes executed after training with the corresponding generated corpora. Also, we propose a novel approach for focused crawling, exploiting the expressive power of multiword expressions.