2026-07-28T23:36:28Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:26699 2026-07-28T09:32:41Z ddc:004 open_access

Optimising Retrieval for Linguistic Question-Answering in European Portuguese: A Benchmark on Ciberdúvidas Da Língua Portuguesa Moura, Pedro Gama, Inês Batista, Fernando Lopes, António Information Retrieval Question-Answering European Portuguese Sentence Encoders Natural Language Processing Information retrieval for question-answering remains underexplored in specialised domains and under-resourced language variants such as European Portuguese. Existing benchmarks largely target general-domain English data and document-centric retrieval, failing to capture the semantic alignment required for linguistic consultation tasks over curated question–answer (QA) pairs. We address this gap by introducing a controlled evaluation framework for retrieval over the "Ciberdúvidas da Língua Portuguesa" corpus, comprising 29,145 expert-validated QA entries. Our approach systematically analyses the interaction between indexing strategies, encoder models, and retrieval paradigms, while modelling real-world query variability through a paraphrase-based benchmark of 600 queries across five user profiles, manually validated by a professional linguist to ensure semantic fidelity. Experiments show that dense retrieval with an IR-optimised monolingual encoder significantly outperforms both sparse (BM25) and hybrid methods, achieving a Mean Reciprocal Rank (MRR) of 0.93. Notably, hybrid retrieval underperforms due to lexical mismatch interference, challenging prevailing assumptions in the literature. Our contributions include a novel benchmark framework for linguistic QA retrieval, empirical evidence supporting monolingual IR-specialised models, and insights into retrieval robustness under paraphrastic variation, enabling improved QA systems for specialised and low-resource environments. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Pedro Moura and Inês Gama and Fernando Batista and António Lopes 2026 Is Part Of OASIcs, Volume 144, 15th Symposium on Languages, Applications and Technologies (SLATE 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.SLATE.2026.1 urn:nbn:de:0030-drops-266997 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2026.1 eng https://creativecommons.org/licenses/by/4.0/legalcode