4 papers
ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT
MikoÅaj Pokrywka, Wojciech Kusa, Mieszko Rutkowski +1
Neural Machine Translation (NMT) has improved translation by using Transformer-based models, but it still struggles with word ambiguity and context. This problem is especially impo…
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…
MultiSlav: Using Cross-Lingual Knowledge Transfer to Combat the Curse of Multilinguality
Artur Kot, MikoÅaj Koszowski, Wojciech Chojnowski +4
Does multilingual Neural Machine Translation (NMT) lead to The Curse of the Multlinguality or provides the Cross-lingual Knowledge Transfer within a language family? In this study,…
Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation
Kamil Guttmann, MikoÅaj Pokrywka, Adrian Charkiewicz +1
This paper explores Minimum Bayes Risk (MBR) decoding for self-improvement in machine translation (MT), particularly for domain adaptation and low-resource languages. We implement…