Question answering dataset for information retrieval in Slovak
PeerJ Computer Science · 05.05.2026 · 12 · e3831
DOI: 10.7717/peerj-cs.3831 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 05.05.2026. Verfasst von Daniel Hládek und 4 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education, Research, Development and Youth of the Slovak Republic, Slovak Research and Development Agency.
Abstract (Originalsprache)
This study introduces a benchmark for evaluating information retrieval in the Slovak language, leveraging a question-answering dataset for fine-tuning and assessment of sentence transformers. The dataset, named Retrieval SkQuAD, is integrated into two widely recognized evaluation frameworks: BEIR (Benchmarking Information Retrieval) and MTEB (Massive Text Embedding Benchmark). Retrieval SkQuAD (Slovak Question Answering Dataset) comprises 19,000 manually annotated answers to 1,134 questions, with each answer assigned a relevance score, and includes information on the usefulness of documents in generating responses. Unlike question answering datasets, this resource provides a nuanced assessment of partial relevance across multiple documents. We fine-tuned several sentence transformers and BERT-based models specifically for retrieving documents containing correct answers within the Slovak Wikipedia. Our fine-tuning process incorporates adversarial questions as hard negatives, leading to significant improvements in retrieval accuracy. Experimental results demonstrate that our approach advances state-of-the-art performance for Slovak information retrieval.
Förderung
- Ministry of Education, Research, Development and Youth of the Slovak Republic
- Slovak Research and Development Agency
Zitieren
APA
Hládek, D., Stromko, M., Sopkovič, K., Pleva, M., & Su, M. (2026). Question answering dataset for information retrieval in Slovak. PeerJ Computer Science, 12, e3831. https://doi.org/10.7717/peerj-cs.3831
Vancouver
Hládek D, Stromko M, Sopkovič K, Pleva M, Su M. Question answering dataset for information retrieval in Slovak. PeerJ Computer Science. 2026;12:e3831. doi:10.7717/peerj-cs.3831
BibTeX
@article{Hldek2026,
author = {Hládek, Daniel and Stromko, Michal and Sopkovič, Kristián and Pleva, Matúš and Su, Ming-Hsiang},
title = {Question answering dataset for information retrieval in Slovak},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3831},
doi = {10.7717/peerj-cs.3831}
}
EUVIMED