no code implementations • 22 Aug 2023 • Agnieszka Mikołajczyk-Bareła, Michał Grochowski
Current research on bias in machine learning often focuses on fairness, while overlooking the roots or causes of bias.
no code implementations • 22 Aug 2023 • Agnieszka Mikołajczyk-Bareła, Maria Ferlin, Michał Grochowski
The development of fair and ethical AI systems requires careful consideration of bias mitigation, an area often overlooked or ignored.
no code implementations • 18 Aug 2023 • Agnieszka Mikołajczyk-Bareła
Three approaches are proposed and discussed: Style Transfer Data Augmentation, Targeted Data Augmentations, and Attribution Feedback.
1 code implementation • 19 Jan 2023 • Maria Ferlin, Sylwia Majchrowska, Marta Plantykow, Alicja Kwaśniwska, Agnieszka Mikołajczyk-Bareła, Milena Olech, Jakub Nalepa
Labeling is the cornerstone of supervised machine learning, which has been exploited in a plethora of various applications, with sign language recognition being one of them.
no code implementations • 28 Sep 2022 • Piotr Pęzik, Agnieszka Mikołajczyk-Bareła, Adam Wawrzyński, Bartłomiej Nitoń, Maciej Ogrodniczuk
The paper explores the relevance of the Text-To-Text Transfer Transformer language model (T5) for Polish (plT5) to the task of intrinsic and extrinsic keyword extraction from short text passages.