Papers and presentations

PolEval 2024 results were presented at a special session of the Natural Language Processing seminar at the Institute of Computer Science, Polish Academy of Sciences on December 2, 2024 in Warsaw.

PolEval 2022/23 overview

• Welcome to PolEval 2024 (Łukasz Kobyliński, Maciej Ogrodniczuk, Filip Graliński, Ryszard Staruch, Karol Saputa)

Task 1: Reading Comprehension

• Task overview (Ryszard Tuora, Aleksandra Zwierzchowska)
• Optimizing LLMs for Polish Reading Comprehension: A Comparative Study of Ensemble and Unified Approaches (Krzysztof Wróbel)

Task 2: Emotion and Sentiment Recognition

• Task overview (Jan Kocoń, Bartłomiej Koptyra)
• Emotion and Sentiment Recognition in Polish Texts Using Large Language Models: A Winning Approach to PolEval 2024 (Krzysztof Wróbel)
• Ensemble as a Variance Reduction Method for Emotion and Sentiment Recognition (Tomasz Warzecha)
• Emotion and Sentiment Recognition using Ensemble Models (Jakub Kosterna)
• Zero-shot Approach Using Bielik LLM for Emotion Recognition in Polish (Paweł Cyrta)

Task 3: Polish Automatic Speech Recognition Challenge

• Task overview (Michał Junczyk, Iwona Christop, Piotr Pęzik)
• Augmenting Polish Automatic Speech Recognition System With Synthetic Data (Łukasz Bondaruk, Jakub Kubiak, Mateusz Czyżnikiewicz)
• Exploration of training Zipformer and E-Branchformer models with Polish language BIGOS dataset (Paweł Cyrta)

The papers were published in PolEval 2024 proceedings volume (ISBN 978-83-63159-33-7).