1 code implementation • RANLP 2021 • Jakub Sido, Ondřej Pražák, Pavel Přibáň, Jan Pašek, Michal Seják, Miloslav Konopík
This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures.
1 code implementation • 27 Jul 2023 • Pavel Přibáň, Ondřej Pražák
We propose a novel end-to-end Semantic Role Labeling model that effectively captures most of the structured semantic information within the Transformer hidden state.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • CRAC (ACL) 2022 • Ondřej Pražák, Miloslav Konopík
This paper describes our approach to the CRAC 2022 Shared Task on Multilingual Coreference Resolution.
1 code implementation • CRAC (ACL) 2022 • Zdeněk Žabokrtský, Miloslav Konopík, Anna Nedoluzhko, Michal Novák, Maciej Ogrodniczuk, Martin Popel, Ondřej Pražák, Jakub Sido, Daniel Zeman, YIlun Zhu
The public edition of CorefUD 1. 0, which contains 13 datasets for 10 languages, was used as the source of training and evaluation data.
2 code implementations • 26 Mar 2022 • Jan Pašek, Jakub Sido, Miloslav Konopík, Ondřej Pražák
This work proposes a new pipeline for leveraging data collected on the Stack Overflow website for pre-training a multimodal model for searching duplicates on question answering websites.
no code implementations • 19 Aug 2021 • Jakub Sido, Michal Seják, Ondřej Pražák, Miloslav Konopík, Václav Moravec
We describe the process of collecting and annotating the data in detail.
no code implementations • RANLP 2021 • Ondřej Pražák, Miloslav Konopík, Jakub Sido
In addition to monolingual experiments, we combine the training data in multilingual experiments and train two joined models -- for Slavic languages and for all the languages together.
1 code implementation • 24 Mar 2021 • Jakub Sido, Ondřej Pražák, Pavel Přibáň, Jan Pašek, Michal Seják, Miloslav Konopík
This paper describes the training process of the first Czech monolingual language representation models based on BERT and ALBERT architectures.
1 code implementation • 30 Nov 2020 • Ondřej Pražák, Pavel Přibáň, Stephen Taylor
In this paper, we describe our method for detection of lexical semantic change (i. e., word sense changes over time) for the DIACR-Ita shared task, where we ranked $1^{st}$.
1 code implementation • SEMEVAL 2020 • Ondřej Pražák, Pavel Přibáň, Stephen Taylor, Jakub Sido
Our method was created for the SemEval 2020 Task 1: \textit{Unsupervised Lexical Semantic Change Detection.}