Eugénio Ribeiro

Assessing LLMs for Culturally Sensitive Communication in European Portuguese

Cost-Effective Hate Speech Detection in Portuguese Using Lightweight LLMs

This work evaluates the efficiency and competitiveness of seven smaller, more accessible LLMs through zero-shot classification with structured instructions, leveraging the expert-annotated test dataset and annotation scheme of the kNOwHATE project to demonstrate a viable, competitive, and low-cost approach that does no...

Evaluating the Prosodic Diversity of TTS Models for L2 Prosody Assessment

Comparisons between L2 speech and TTS-based references reveal both the potential and the limitations of using synthetic speech for prosody assessment.

An OWL/RDF Ontology for Declarative User Interface Generation

OntologyToUI is presented, a framework that treats ontologies written in OWL/RDF as a Domain-Specific Language (DSL) for user-interface specification and validate the framework’s extensibility through two case studies developed in the scope of the Smart_LEM project.

From Natural Language to Structured Queries An LLM-Powered Chatbot for a Smart Tourism Observatory

A specialized conversational agent that facilitates discovery through a filter-based natural language interface that uses prompt engineering – specifically, one-shot Chain-of-Thought (CoT) reasoning – to generate boolean search queries (BSQs).

Polarizations in Static Word Embeddings: Investigating Bias in Marginalized Dialects of Portuguese

It is suggested that static word embeddings applied to Pajubá fail to capture the sociolinguistic complexity of Pajubá and systematically reflect the dominant and often discriminatory discourses present in the training corpora.

Inter-Sentential Relations in Enhanced Lexicalized Meaning Representation (E-LMR)

E-LMR is positioned as a viable alternative within a modular semantic architecture where discourse relations are explicitly encoded while remaining tightly coupled to lexical form and improves interpretability, annotation consistency, and cross-linguistic robustness.

Lazarus: Where Compilers Meet Education

This paper presents both the source language, and its register-based virtual machine, while discussing an often neglected feature in compiler design: the incremental parser.

Out of the Loop No More: Online Abstract Debugging with Loop Stepping

This paper proposes online abstract debugging, which performs abstract interpretation on demand as the developer steps through the program, and instantiate this model for WebAssembly and presents a prototype implementation, demonstrating that developers can effectively draw sound conclusions about complex, potentially...

OntoExpand: SPARQL-Based Ontology Expansion and Reasoning

OntoExpand is introduced, a new methodology for ontology expansion that uses SPARQL CONSTRUCT queries as an efficient alternative to conventional reasoning techniques that improves performance, reduces computational overhead, is pattern driven allowing a more granular expansion control and seamlessly integrates with SP...

Gender Bias Evaluation in English-Portuguese Automated Translation Outputs

This work contributes a preliminary cross-system comparison for an underexplored language pair and lays the groundwork for larger-scale evaluations of gender-inclusive AT, indicating that all four models struggle to faithfully convey gender information from source to target.

RI: A DSL for Software Development Project Continuous Configuration

A Domain-Specific Language (DSL), named RI language, designed for the declarative description of microservices, along with a supporting tool, TSE (Toolbox Service Executor), implemented in Python and based on the RI grammar, enables the representation of structural and operational aspects of services in a technology-ag...