1 code implementation • Findings (ACL) 2022 • Piotr Przybyła, Matthew Shardlow
The environmental costs of research are progressively important to the NLP community and their associated challenges are increasingly debated.
1 code implementation • 14 Mar 2023 • Piotr Przybyła, Alexander Shvets, Horacio Saggion
Text classification methods have been widely investigated as a way to detect content of low credibility: fake news, social media bots, propaganda, etc.
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 • 21 Nov 2022 • Matthew Shardlow, Piotr Przybyła
However, here we take the position that such a large language model cannot be sentient, or conscious, and that LaMDA in particular exhibits no advances over other similar models that would qualify it.
1 code implementation • Findings (ACL) 2021 • Laura Vásquez-Rodríguez, Matthew Shardlow, Piotr Przybyła, Sophia Ananiadou
Modern text simplification (TS) heavily relies on the availability of gold standard data to build machine learning models.
no code implementations • 22 Oct 2017 • Piotr Przybyła
In this paper, the problem of disambiguating a target word for Polish is approached by searching for related words with known meaning.
no code implementations • 27 May 2016 • Piotr Przybyła
In this paper an open-domain factoid question answering system for Polish, RAFAEL, is presented.