no code implementations • EAMT 2022 • Artur Nowakowski, Krzysztof Jassem, Maciej Lison, Rafał Jaworski, Tomasz Dwojak, Karolina Wiater, Olga Posesor
This paper reports on the implementation and deployment of an MT system in the Polish branch of EY Global Limited.
no code implementations • EAMT 2022 • Artur Nowakowski, Krzysztof Jassem, Maciej Lison, Kamil Guttmann, Miko Pokrywka
We introduce POLENG MT, an MT platform that may be used as a cloud web application or as an on-site solution.
no code implementations • Findings (NAACL) 2022 • Jakub Pokrywka, Filip Graliński, Krzysztof Jassem, Karol Kaczmarek, Krzysztof Jurkiewicz, Piotr Wierzchon
The aim of the paper is to apply, for historical texts, the methodology used commonly to solve various NLP tasks defined for contemporary data, i. e. pre-train and fine-tune large Transformer models.
no code implementations • MTSummit 2021 • Artur Nowakowski, Krzysztof Jassem
The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language.
no code implementations • MTSummit 2021 • Artur Nowakowski, Krzysztof Jassem
To this end, a method based on constrained decoding that incorporates an inflected lexicon into a neural translation process was applied in the engine.
no code implementations • 2 Feb 2024 • Kacper Dudzic, Filip Graliński, Krzysztof Jassem, Marek Kubis, Piotr Wierzchoń
This paper discusses two approaches to the diachronic normalization of Polish texts: a rule-based solution that relies on a set of handcrafted patterns, and a neural normalization model based on the text-to-text transfer transformer architecture.
no code implementations • 24 Aug 2021 • Artur Nowakowski, Krzysztof Jassem
We share this dataset and create a new task for the detection of criminal texts using the Gonito platform as the benchmark.