5 papers
ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation
Michał Ciesiółka, Dawid Wiśniewski, Adrian Charkiewicz +1
We present ForMaT (Format-Preserving Multilingual Translation), a parallel corpus of 3,956 PDFs across 15 language pairs that preserves original layout metadata proposed for multim…
Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation
Dawid Wisniewski, Igor Czudy
Preserving affective nuance remains a challenge in Machine Translation (MT), where semantic equivalence often takes precedence over emotional fidelity. This paper evaluates the per…
Do Not Change Me: On Transferring Entities Without Modification in Neural Machine Translation -- a Multilingual Perspective
Dawid Wisniewski, Mikolaj Pokrywka, Zofia Rostek
Current machine translation models provide us with high-quality outputs in most scenarios. However, they still face some specific problems, such as detecting which entities should…
Exploring the Feasibility of Multilingual Grammatical Error Correction with a Single LLM up to 9B parameters: A Comparative Study of 17 Models
Dawid Wisniewski, Antoni Solarski, Artur Nowakowski
Recent language models can successfully solve various language-related tasks, and many understand inputs stated in different languages. In this paper, we explore the performance of…
FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes
Dawid Wiśniewski, Zofia Rostek, Artur Nowakowski
People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus…