no code implementations • EACL (BSNLP) 2021 • Robert Mroczkowski, Piotr Rybak, Alina Wróblewska, Ireneusz Gawlik
Therefore, this paper presents the first ablation study focused on Polish, which, unlike the isolating English language, is a fusional language.
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).
no code implementations • 17 Dec 2022 • Piotr Rybak, Piotr Przybyła, Maciej Ogrodniczuk
Recently proposed systems for open-domain question answering (OpenQA) require large amounts of training data to achieve state-of-the-art performance.
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.
no code implementations • 9 May 2023 • Piotr Rybak
Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers.
no code implementations • 15 Sep 2023 • Piotr Rybak, Maciej Ogrodniczuk
However, most of the work concerns popular languages such as English or Chinese.
no code implementations • 22 Feb 2024 • Piotr Rybak
Pre-trained language models have revolutionized the natural language understanding landscape, most notably BERT (Bidirectional Encoder Representations from Transformers).
no code implementations • 7 Mar 2024 • Martyna Wiącek, Piotr Rybak, Łukasz Pszenny, Alina Wróblewska
Aware of the shortcomings of existing NLPre evaluation approaches, we investigate a novel method of reliable and fair evaluation and performance reporting.
1 code implementation • ACL 2020 • Piotr Rybak, Robert Mroczkowski, Janusz Tracz, Ireneusz Gawlik
To ensure a common evaluation scheme and promote models that generalize to different NLU tasks, the benchmark includes datasets from varying domains and applications.
1 code implementation • CONLL 2018 • Piotr Rybak, Alina Wróblewska
This paper describes the ICS PAS system which took part in CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies.