http://hdl.handle.net/10174/1005 2026-04-03T14:14:23Z 2026-04-03T14:14:23Z Lamar-Leon, Javier Nogueira, Vitor Salgueiro, Pedro Quaresma, Paulo http://hdl.handle.net/10174/41416 2026-02-23T15:53:07Z 2026-01-04T00:00:00Z

Title: Describing Land Cover Changes via Multi-Temporal Remote Sensing Image Captioning Using LLM, ViT, and LoRA Authors: Lamar-Leon, Javier; Nogueira, Vitor; Salgueiro, Pedro; Quaresma, Paulo Editors: Pan, Jiayi; Li, Xinghua Abstract: Describing land cover changes from multi-temporal remote sensing imagery requires capturing both visual transformations and their semantic meaning in natural language. Existing methods often struggle to balance visual accuracy with descriptive coherence. We propose MVLT-LoRA-CC (Multi-modal Vision Language Transformer with Low-Rank Adaptation for Change Captioning), a framework that integrates a Vision Transformer (ViT), a Large Language Model (LLM), and Low-Rank Adaptation (LoRA) for efficient multi-modal learning. The model processes paired temporal images through patch embeddings and transformer blocks, aligning visual and textual representations via a multi-modal adapter. To improve efficiency and avoid unnecessary parameter growth, LoRA modules are selectively inserted only into the attention projection layers and cross-modal adapter blocks rather than being uniformly applied to all linear layers. This targeted design preserves general linguistic knowledge while enabling effective adaptation to remote sensing change description. To assess performance, we introduce the Complementary Consistency Score (CCS) framework, which evaluates both descriptive fidelity for change instances and classification accuracy for no change cases. Experiments on the LEVIR-CC test set demonstrate that MVLT-LoRA-CC generates semantically accurate captions, surpassing prior methods in both descriptive richness and temporal change recognition. The approach establishes a scalable solution for multi-modal land cover change description in remote sensing applications.

2026-01-04T00:00:00Z Iznaga, Yanet Rato, Luís Salgueiro, Pedro León, Javier http://hdl.handle.net/10174/41311 2026-02-19T11:46:51Z 2025-10-17T23:00:00Z

Title: Integrating Large Language Models into Automated Software Testing Authors: Iznaga, Yanet; Rato, Luís; Salgueiro, Pedro; León, Javier Editors: Bellavista, Paolo Abstract: This work investigates the use of LLMs to enhance automation in software testing, with a particular focus on generating high-quality, context-aware test scripts from natural language descriptions, while addressing both text-to-code and text+code-to-code generation tasks. The Codestral Mamba model was fine-tuned by proposing a way to integrate LoRA matrices into its architecture, enabling efficient domain-specific adaptation and positioning Mamba as a viable alternative to Transformer-based models. The model was trained and evaluated on two benchmark datasets: CONCODE/CodeXGLUE and the proprietary TestCase2Code dataset. Through structured prompt engineering, the system was optimized to generate syntactically valid and semantically meaningful code for test cases. Experimental results demonstrate that the proposed methodology successfully enables the automatic generation of code-based test cases using large language models. In addition, this work reports secondary benefits, including improvements in test coverage, automation efficiency, and defect detection when compared to traditional manual approaches. The integration of LLMs into the software testing pipeline also showed potential for reducing time and cost while enhancing developer productivity and software quality. The findings suggest that LLM-driven approaches can be effectively aligned with continuous integration and deployment workflows. This work contributes to the growing body of research on AI-assisted software engineering and offers practical insights into the capabilities and limitations of current LLM technologies for testing automation.

2025-10-17T23:00:00Z Medeiros, Eduardo Corado, Leonel Rato, Luís Quaresma, Paulo Salgueiro, Pedro http://hdl.handle.net/10174/41221 2026-02-16T15:16:13Z 2023-04-23T23:00:00Z

Title: Domain Adaptation Speech-to-Text for Low-Resource European Portuguese Using Deep Learning Authors: Medeiros, Eduardo; Corado, Leonel; Rato, Luís; Quaresma, Paulo; Salgueiro, Pedro Editors: Reina, Daniel Gutiérrez Abstract: Automatic speech recognition (ASR), commonly known as speech-to-text, is the process of transcribing audio recordings into text, i.e., transforming speech into the respective sequence of words. This paper presents a deep learning ASR system optimization and evaluation for the European Portuguese language. We present a pipeline composed of several stages for data acquisition, analysis, pre-processing, model creation, and evaluation. A transfer learning approach is proposed considering an English language-optimized model as starting point; a target composed of European Portuguese; and the contribution to the transfer process by a source from a different domain consisting of a multiple-variant Portuguese language dataset, essentially composed of Brazilian Portuguese. A domain adaptation was investigated between European Portuguese and mixed (mostly Brazilian) Portuguese. The proposed optimization evaluation used the NVIDIA NeMo framework implementing the QuartzNet15×5 architecture based on 1D time-channel separable convolutions. Following this transfer learning data-centric approach, the model was optimized, achieving a state-of-the-art word error rate (WER) of 0.0503.

2023-04-23T23:00:00Z L. M. Pereira, João Fonseca, Manuel J. Lopes, Antónia Galhardas, Helena http://hdl.handle.net/10174/40223 2026-01-07T22:11:00Z 2024-02-15T00:00:00Z

Title: Cleenex: Support for User Involvement During an Iterative Data Cleaning Process Authors: L. M. Pereira, João; Fonseca, Manuel J.; Lopes, Antónia; Galhardas, Helena Editors: Demartini, Gianluca; Sadiq, Shazia; Yang, Jie Abstract: The existence of large amounts of data increases the probability of occurring data quality problems. A data cleaning process that corrects these problems is usually an iterative process because it may need to be re-executed and refined to produce high quality data. Moreover, due to the specificity of some data quality problems and the limitation of data cleaning programs to cover all problems, often a user has to be involved during the program executions by manually repairing data. However, there is no data cleaning framework that appropriately supports this involvement in such an iterative process, a form of human-in-the-loop, to clean structured data. Moreover, data preparation tools that somehow involve the user in data cleaning processes have not been evaluated with real users to assess their effort. Therefore, we propose Cleenex, a data cleaning framework with support for user involvement during an iterative data cleaning process and conducted two data cleaning experimental evaluations: an assessment of the Cleenex components that support the user when manually repairing data with a simulated user, and a comparison, in terms of user involvement, of data preparation tools with real users. Results show that Cleenex components reduce the user effort when manually cleaning data during a data cleaning process, for example the number of tuples visualized is reduced in 99%. Moreover, when performing data cleaning tasks with Cleenex, real users need less time/effort (e.g., half the clicks) and, based on questionnaires, prefer it to the other tools used for comparison, OpenRefine and Pentaho Data Integration

2024-02-15T00:00:00Z