Evaluation of Few-Shot Learning for Classification Tasks in the Polish Language

no code implementations • 27 Apr 2024 • Tsimur Hadeliya, Dariusz Kajtoch

Our findings reveal that ICL achieves the best performance, with commercial models like GPT-3. 5 and GPT-4 attaining the best performance.

Few-Shot Learning In-Context Learning

Going beyond research datasets: Novel intent discovery in the industry setting

no code implementations • 9 May 2023 • Aleksandra Chrabrowa, Tsimur Hadeliya, Dariusz Kajtoch, Robert Mroczkowski, Piotr Rybak

We also devise the best method to utilize the conversational structure (i. e., question and answer) of real-life datasets during fine-tuning for clustering tasks, which we call Conv.

Clustering Intent Discovery

Evaluation of Transfer Learning for Polish with a Text-to-Text Model

no code implementations • LREC 2022 • Aleksandra Chrabrowa, Łukasz Dragan, Karol Grzegorczyk, Dariusz Kajtoch, Mikołaj Koszowski, Robert Mroczkowski, Piotr Rybak

We evaluate the performance of plT5, mT5, Polish BART (plBART), and Polish GPT-2 (papuGaPT2).

Decoder Denoising +2