Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Jukić, Josip"'
Autor:
Jukić, Josip, Šnajder, Jan
Enhancing generalization and uncertainty quantification in pre-trained language models (PLMs) is crucial for their effectiveness and reliability. Building on machine learning research that established the importance of robustness for improving genera
Externí odkaz:
http://arxiv.org/abs/2404.00758
Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training. We present a novel meth
Externí odkaz:
http://arxiv.org/abs/2310.02832
Autor:
Jukić, Josip, Šnajder, Jan
Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages. Active learning (AL), a set of algorithms designed to decrease labeling costs by minimizing la
Externí odkaz:
http://arxiv.org/abs/2305.14576
Active learning (AL) aims to reduce labeling costs by querying the examples most beneficial for model learning. While the effectiveness of AL for fine-tuning transformer-based pre-trained language models (PLMs) has been demonstrated, it is less clear
Externí odkaz:
http://arxiv.org/abs/2305.09807
Expressing attitude or stance toward entities and concepts is an integral part of human behavior and personality. Recently, evaluative language data has become more accessible with social media's rapid growth, enabling large-scale opinion analysis. H
Externí odkaz:
http://arxiv.org/abs/2302.00493
Autor:
Jukić, Josip, Šnajder, Jan
Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning. While recent work has demonstrated the benefit of using AL in combination with large pre-trained language models (P
Externí odkaz:
http://arxiv.org/abs/2212.11680
A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component. A common practice for evaluating whether an interpretability method is faithful has bee
Externí odkaz:
http://arxiv.org/abs/2211.08369
Supervised machine learning has become the cornerstone of today's data-driven society, increasing the need for labeled data. However, the process of acquiring labels is often expensive and tedious. One possible remedy is to use active learning (AL) -
Externí odkaz:
http://arxiv.org/abs/2211.06224
Autor:
Barković, Dražen, Jukić, Josip
Publikováno v:
EKONOMSKI VJESNIK / ECONVIEWS : REVIEW OF CONTEMPORARY BUSINESS, ENTREPRENEURSHIP AND ECONOMIC ISSUES. 30(2):287-300
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=600546
Autor:
Homolak, Jan, Barešić, Anja, Jukić, Josip, Košec, Andro, Žižak, Mirza, Petrak, Jelka, Škorić, Lea, Lisac, Mirjana
Prednosti korištenja umjetne inteligencije (AI) u medicini: 1) Poboljšanje dijagnostike: AI može poboljšati dijagnostiku različitih bolesti i stanja tako što može analizirati ogromne količine podataka, prepoznati uzorke i identificirati čak
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=57a035e5b1ae::59f345a160c01a4034d49aa80d4b71f1
https://www.bib.irb.hr/1270850
https://www.bib.irb.hr/1270850