1 code implementation • 3 Apr 2024 • Jakub Hoscilowicz, Pawel Pawlowski, Marcin Skorupa, Marcin Sowański, Artur Janicki
In the on-device scenario (tiny and not pretrained SLU), our method improved the Overall Accuracy from 5. 31% to 22. 06% over the baseline Global-Local Contrastive Learning Framework (GL-CLeF) method.
2 code implementations • 25 Oct 2023 • Marek Kubis, Paweł Skórzewski, Marcin Sowański, Tomasz Ziętkiewicz
This paper proposes a method for investigating the impact of speech recognition errors on the performance of natural language understanding models.
no code implementations • 27 Jan 2023 • Jakub Hościłowicz, Marcin Sowański, Piotr Czubowski, Artur Janicki
In this article, we use probing to investigate phenomena that occur during fine-tuning and knowledge distillation of a BERT-based natural language understanding (NLU) model.