Zobrazeno 1 - 4
of 4
pro vyhledávání: '"GUTTMANN, KAMIL"'
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 the self-improvement process by fine-tuning the model on its MBR-decod
Externí odkaz:
http://arxiv.org/abs/2405.11937
This paper presents Adam Mickiewicz University's (AMU) submissions to the constrained track of the WMT 2022 General MT Task. We participated in the Ukrainian $\leftrightarrow$ Czech translation directions. The systems are a weighted ensemble of four
Externí odkaz:
http://arxiv.org/abs/2209.02962
Publikováno v:
Artur Nowakowski
This paper presents Adam Mickiewicz University's (AMU) submissions to the constrained track of the WMT 2022 General MT Task. We participated in the Ukrainian $\leftrightarrow$ Czech translation directions. The systems are a weighted ensemble of four
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cebd88189ea75bef2f69ec16602762a2
http://arxiv.org/abs/2209.02962
http://arxiv.org/abs/2209.02962
Autor:
GUTTMANN, KAMIL1
Publikováno v:
Digital Engineering. feb/mar2021, Issue 1, p42-43. 2p.