2 code implementations • 11 Apr 2024 • Anton Schäfer, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel, Imanol Schlag
In controlled experiments on perfectly equivalent cloned languages, we observe that the existence of a predominant language during training boosts the performance of less frequent languages and leads to stronger alignment of model representations across languages.
2 code implementations • 9 Apr 2024 • Anton Schäfer, Thomas Hofmann, Imanol Schlag, Tiago Pimentel
In this paper, we study the impact of near duplicate subwords on LM training efficiency.
no code implementations • 3 Nov 2020 • Anton Schäfer, Nils Blach, Oliver Rausch, Maximilian Warm, Nils Krüger
Professionals in modern healthcare systems are increasingly burdened by documentation workloads.