The CEDMO project supports the open-access and open-science spirit. The following list contains selected high-impact publications and datasets that were created as a part of our activities related to the research and development of AI-based solutions.
Publication
Multilingual Previously Fact-Checked Claim Retrieval
Authors
Pikuliak, M., Srba, I., Moro, R., Hromadka, T., Smoleň, T., Melišek, M., Vykopal, I., Simko, J., Podroužek, J., Bielikova, M.
Published in
EMNLP ’23: Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2023
Dataset
MultiClaim: Multilingual Previously Fact-Checked Claim Retrieval Dataset
Authors
Pikuliak, M., Srba, I., Moro, R., Hromadka, T., Smoleň, T., Melišek, M., Vykopal, I., Simko, J., Podroužek, J., Bielikova, M.
Publication
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness
Authors
Čegiň, J., Šimko, J., Brusilovsky, P.
Published in
EMNLP ’23: Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2023
Publication
Auditing YouTube’s Recommendation Algorithm for Misinformation Filter Bubbles
Authors
Srba, I., Moro, R., Tomlein, M., Pecher, B., Simko, J., Stefancova, E., Kompan, M., Hrckova, A., Podrouzek, J., Gavornik, A., Bielikova, M.
Published in
ACM TORS: ACM Transactions on Recommender Systems, 2023
Publication
A Game for Crowdsourcing Adversarial Examples for False Information Detection
Authors
Čegiň, J., Šimko, J., Brusilovsky, P.
Published in
AIofAI ‘22: Proceedings of the 2nd Workshop on Adverse Impacts and Collateral Effects of Artificial Intelligence Technologies, 2022
Publication
SlovakBERT: Slovak Masked Language Model
Authors
Pikuliak, M., Grivalsky, S., Konopka, M., Blstak, M., Tamajka, M., Bachraty, V., Simko, M., Balazik, P., Trnka, M., Uhlarik F.
Published in
Findings of the Association for Computational Linguistics: EMNLP 2022