Linking citizen complaints to the public services they concern remains a major challenge in the Brazilian federal administration. In 2025, over 1.2 million manifestations were submitted across 328 agencies, yet only about 1.8% are currently associated with a specific service, limiting large-scale monitoring and evidence-based management. We cast this task as an extreme multi-class text classification problem marked by severe class imbalance and strong lexical–semantic gaps between citizen language and official service descriptions. Building on recent work that reframes the task as information retrieval, we combine sparse retrieval with BM25 over representative complaint corpora and dense retrieval enriched with RAG-labels: semantically expanded label descriptions generated via Retrieval-Augmented Generation and Small Language Models. This approach markedly reduces vocabulary mismatch and semantic ambiguity, yielding substantial gains over direct text or embedding matching. To our knowledge, this is the first Portuguese-language application of RAG-labels for service–complaint association. In real operational data from the Federal Ombudsman Office, our method can automatically assign plausible services to roughly 73% of previously unlabeled cases, improving coverage and supporting more effective public service evaluation.

We investigate two essential challenges in the context of hierarchical topic modeling (HTM)—(i) the impact of data representation and (ii) topic evaluation. The data representation directly influences the performance of the topic generation, and the impact of new representations such as contextual embeddings in this task has been under-investigated. Topic evaluation, responsible for driving the advances in the field, assesses the overall quality of the topic generation process. HTM studies exploit the exact topic modeling (TM) evaluation metrics as traditional TM to measure the quality of topics. One significant result of our work is demonstrating that the HTM’s hierarchical nature demands novel ways of evaluating the quality of topics. As our main contribution, we propose two new topic quality metrics to assess the topical quality of the hierarchical structures. Uniqueness considers topic topological consistency, while the Semantic Hierarchical Structure (SHS) captures the semantic relatedness of the hierarchies. We also present an additional advance to the state-of-the-art by proposing the c-CluHTM. To the best of our knowledge, c-CluHTM is the first method that exploits contextual embeddings into NMF in HTM tasks. c-CluHTM enhances the topics’ semantics while preserving the hierarchical structure. We perform an experimental evaluation, and our results demonstrate the superiority of our proposal with gains between 12% and 21%, regarding NPMI and Coherence over the best baselines. Regarding the newly proposed metrics, our results reveal that Uniqueness and SHS can capture relevant information about the structure of the hierarchical topics that traditional metrics cannot.

This study describes the development of a Portuguese Community-Question Answering benchmark in the domain of Diabetes Mellitus using a Recognizing Question Entailment (RQE) approach. Given a premise question, RQE aims to retrieve semantically similar, already answered, archived questions. We build a new Portuguese benchmark corpus with 785 pairs between premise questions and archived answered questions marked with relevance judgments by medical experts. Based on the benchmark corpus, we leveraged and evaluated several RQE approaches ranging from traditional information retrieval methods to novel large pre-trained language models and ensemble techniques using learn-to-rank approaches. Our experimental results show that a supervised transformer-based method trained with multiple languages and for multiple tasks (MUSE) outperforms the alternatives. Our results also show that ensembles of methods (stacking) as well as a traditional (light) information retrieval method (BM25) can produce competitive results. Finally, among the tested strategies, those that exploit only the question (not the answer), provide the best effectiveness-efficiency trade-off. Code is publicly available.