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...
Mauro Cardoso, Eugénio Ribeiro, F. Batista et al.· 0 citations
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).
Rodrigo Simões, A. Lopes, Fernando Brito et al.· 0 citations
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.
Raimundo Juracy, Campos Ferro, Eugénio Ribeiro et al.· 0 citations
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.
Jorge Baptista, Fernando Batista, Eugénio Ribeiro et al.· 0 citations
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.
R. Gonçalves, P. Henriques, J. Ramalho et al.· 0 citations
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...
Vitor Lelis, N. Leite, José Carlos et al.· 0 citations
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.
Xiao-Lan Xu, Sara Mendes, F. Batista et al.· 0 citations
A novel benchmark framework for linguistic QA retrieval, empirical evidence supporting monolingual IR-specialised models, and insights into retrieval robustness under paraphrastic variation are included, enabling improved QA systems for specialised and low-resource environments.
Pedro Moura, Inês Gama, F. Batista et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.