EREugénio Ribeiro

Eugénio Ribeiro

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Eugénio Ribeiro has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Cognitive Network Approach to Exploring Semantic and Emotional Patterns in Anxiety and Depression Narratives

    by Cláudia Calaboiça, Anita Santos, Liliana Meira, Eugénio Ribeiro, Andreia Sofia Teixeira, Tiago Bento Ferreira


  • Open Access

    Aprendizado por Transferência para Correção Automática de Redação

    by Igor Cataneo Silveira, Eugénio Ribeiro, Nuno Mamede, Jorge Baptista

    A tarefa de Correção Automática de Redação tem despertado crescente interesse na área de processamento de texto em português. Entre os conjuntos de dados disponíveis, destaca-se um corpus de redações narrativas produzidas por alunos do 5º ao 9º ano do ensino fundamental no Brasil. Essas redações são avaliadas segundo quatro competências: registro formal, coerência temática, estrutura retórica narrativa e coesão textual. Este trabalho explora a criação de um sistema baseado em conhecimentos derivados de outro dataset (desenvolvido com base em textos produzidos para o ENEM) e de outras tarefas (cálculo de complexidade textual e análise de legibilidade). O sistema desenvolvido combina modelos neurais, características (features) curadas calculadas por programas de análise textual e seleção de features em um modelo de Aprendizado em Dois Estágios. Com isso, foi possível elevar a performance em relação ao estado-da-arte, nomeadamente, em 9% para a primeira competência, 5,5% para a terceira e 8,9% para a quarta.


  • Open Access

    Story Generation from Visual Inputs: Techniques, Related Tasks, and Challenges

    by Daniel A. P. Oliveira, Eugénio Ribeiro, David Martins de Matos

    Creating engaging narratives from visual data is crucial for automated digital media consumption, assistive technologies, and interactive entertainment. This survey covers methodologies used in the generation of these narratives, focusing on their principles, strengths, and limitations. The survey also covers tasks related to automatic story generation, such as image and video captioning, and Visual Question Answering. These tasks share common challenges with Visual Story Generation (VSG) and have served as inspiration for the techniques used in the field. We analyze the main datasets and evaluation metrics, providing a critical perspective on their limitations.


  • Open Access

    INESC-ID @ eRisk 2025: Exploring Fine-Tuned, Similarity-Based, and Prompt-Based Approaches to Depression Symptom Identification

    by Diogo A. P. Nunes, Eugénio Ribeiro

    In this work, we describe our team's approach to eRisk's 2025 Task 1: Search for Symptoms of Depression. Given a set of sentences and the Beck's Depression Inventory - II (BDI) questionnaire, participants were tasked with submitting up to 1,000 sentences per depression symptom in the BDI, sorted by relevance. Participant submissions were evaluated according to standard Information Retrieval (IR) metrics, including Average Precision (AP) and R-Precision (R-PREC). The provided training data, however, consisted of sentences labeled as to whether a given sentence was relevant or not w.r.t. one of BDI's symptoms. Due to this labeling limitation, we framed our development as a binary classification task for each BDI symptom, and evaluated accordingly. To that end, we split the available labeled data into training and validation sets, and explored foundation model fine-tuning, sentence similarity, Large Language Model (LLM) prompting, and ensemble techniques. The validation results revealed that fine-tuning foundation models yielded the best performance, particularly when enhanced with synthetic data to mitigate class imbalance. We also observed that the optimal approach varied by symptom. Based on these insights, we devised five independent test runs, two of which used ensemble methods. These runs achieved the highest scores in the official IR evaluation, outperforming submissions from 16 other teams.

  • Open Access

    Exploring Few-Shot Approaches to Automatic Text Complexity Assessment in European Portuguese

    by Eugénio Ribeiro, David Antunes, Nuno Mamede, Jorge Baptista

    The automatic assessment of text complexity has an important role to play in the context of language education. In this study, we shift the focus from L2 learners to adult native speakers with low literacy by exploring the new iRead4Skills dataset in European Portuguese. Furthermore, instead of relying on classical machine learning approaches or fine-tuning a pre-trained language model, we leverage the capabilities of prompt-based Large Language Models (LLMs), with a special focus on few-shot prompting approaches. We explore prompts with varying degrees of information, as well as different example selection approaches. Overall, the results of our experiments reveal that even a single example significantly increases the performance of the model and that few-shot approaches generalize better than fine-tuned models. However, automatic complexity assessment is a difficult and highly subjective task that is still far from solved.


  • Open Access

    Avaliação Automática do Nível de Complexidade de Textos em Português Europeu

    by Eugénio Ribeiro, Nuno Mamede, Jorge Baptista

    A avaliação da inteligibilidade de textos e a sua classificação por níveis de complexidade é essencial para o ensino de língua e para indústrias relacionadas com a linguagem que dependem de uma comunicação eficaz. O Quadro Europeu Comum de Referência para as Línguas (CEFR) é uma referência amplamente reconhecida para a classificação dos níveis de proficiência linguística. Este quadro pode ser utilizado não apenas para avaliar a proficiência de aprendentes de uma língua, mas também, de uma perspetiva de inteligibilidade, como um meio de identificar a proficiência necessária para compreender um texto. O objetivo deste estudo é desenvolver e avaliar modelos automáticos capazes de classificar textos em português europeu de acordo com os níveis de complexidade definidos pelo CEFR. Para tal, exploramos o ajuste de vários modelos de base pré-treinados em dados textuais utilizados para fins de avaliação de proficiência e exploramos abordagens que tiram partido da natureza ordinal dos níveis. Realizamos ainda uma análise preliminar da capacidade de base que modelos baseados em instruções têm para desempenhar esta tarefa. Nas experiências, os melhores modelos conseguem atingir mais de 80% de taxa de acerto e 75% de medida F1 mas têm dificuldade em generalizar para diferentes tipos de texto, o que revela a necessidade de dados de treino adicionais e mais diversificados.


  • Open Access

    Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation (Extended Abstract)

    by Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos

    From the perspective of a dialog system, the identification of the intention behind the segments in a dialog is important, as it provides cues regarding the information present in the segments and how they should be interpreted. The ISO 24617-2 standard for dialog act annotation defines a hierarchically organized set of general-purpose communicative functions that correspond to different intentions that are relevant in the context of a dialog. In this paper, we explore the automatic recognition of these functions. To do so, we propose to adapt existing approaches to dialog act recognition, so that they can deal with the hierarchical classification problem. More specifically, we propose the use of an end-to-end hierarchical network with cascading outputs and maximum a posteriori path estimation to predict the communicative function at each level of the hierarchy, preserve the dependencies between the functions in the path, and decide at which level to stop. Additionally, we rely on transfer learning processes to address the data scarcity problem. Our experiments on the DialogBank show that this approach outperforms both flat and hierarchical approaches based on multiple classifiers and that each of its components plays an important role in the recognition of general-purpose communicative functions.

  • Open Access

    Towards Learning Through Open-Domain Dialog

    by Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos

    The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change how we relate to them. However, research in this area is practically nonexistent. In this paper, we identify the modifications required for a dialog system to be able to learn from the dialog and propose generic approaches that can be used to implement those modifications. More specifically, we discuss how knowledge can be extracted from the dialog, used to update the agent's semantic network, and grounded in action and observation. This way, we hope to raise awareness for this subject, so that it can become a focus of research in the future.

  • Using Topic Information to Improve Non-exact Keyword-Based Search for Mobile Applications

    by Eugénio Ribeiro, Ricardo Ribeiro, Fernando Batista, João Oliveira

    Considering the wide offer of mobile applications available nowadays, effective search engines are imperative for an user to find applications that provide a specific desired functionality. Retrieval approaches that leverage topic similarity between queries and applications have shown promising results in previous studies. However, the search engines used by most app stores are based on keyword-matching and boosting. In this paper, we explore means to include topic information in such approaches, in order to improve their ability to retrieve relevant applications for non-exact queries, without impairing their computational performance. More specifically, we create topic models specialized on application descriptions and explore how the most relevant terms for each topic covered by an application can be used to complement the information provided by its description. Our experiments show that, although these topic keywords are not able to provide all the information of the topic model, they provide a sufficiently informative summary of the topics covered by the descriptions, leading to improved performance.


  • Open Access

    Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations

    by Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos

    Automatic dialog act recognition is a task that has been widely explored over the years. In recent works, most approaches to the task explored different deep neural network architectures to combine the representations of the words in a segment and generate a segment representation that provides cues for intention. In this study, we explore means to generate more informative segment representations, not only by exploring different network architectures, but also by considering different token representations, not only at the word level, but also at the character and functional levels. At the word level, in addition to the commonly used uncontextualized embeddings, we explore the use of contextualized representations, which are able to provide information concerning word sense and segment structure. Character-level tokenization is important to capture intention-related morphological aspects that cannot be captured at the word level. Finally, the functional level provides an abstraction from words, which shifts the focus to the structure of the segment. Additionally, we explore approaches to enrich the segment representation with context information from the history of the dialog, both in terms of the classifications of the surrounding segments and the turn-taking history. This kind of information has already been proved important for the disambiguation of dialog acts in previous studies. Nevertheless, we are able to capture additional information by considering a summary of the dialog history and a wider turn-taking context. By combining the best approaches at each step, we achieve performance results that surpass the previous state-of-the-art on generic dialog act recognition on both the Switchboard Dialog Act Corpus (SwDA) and the ICSI Meeting Recorder Dialog Act Corpus (MRDA), which are two of the most widely explored corpora for the task. Furthermore, by considering both past and future context, similarly to what happens in an annotation scenario, our approach achieves a performance similar to that of a human annotator on SwDA and surpasses it on MRDA.