8 citations · 15 across the 7 of their papers we have counts for
3 papers · 1 filter
Subword-Delimited Downsampling for Better Character-Level Translation
Lukas Edman, Antonio Toral, Gertjan van Noord
Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more d…
Patching Leaks in the Charformer for Efficient Character-Level Generation
Lukas Edman, Antonio Toral, Gertjan van Noord
Character-based representations have important advantages over subword-based ones for morphologically rich languages. They come with increased robustness to noisy input and do not…
The Importance of Context in Very Low Resource Language Modeling
Lukas Edman, Antonio Toral, Gertjan van Noord
This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available. We find that, in very low resource scenarios, statistical…