216 citations · 427 across the 19 of their papers we have counts for
20 papers
Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation
Lukas Edman, Gabriele Sarti, Antonio Toral +2
Pretrained character-level and byte-level language models have been shown to be competitive with popular subword models across a range of Natural Language Processing (NLP) tasks. H…
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…
Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer
Ahmet Üstün, Arianna Bisazza, Gosse Bouma +2
Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is availa…
Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
Lukas Edman, Ahmet Üstün, Antonio Toral +1
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German--Lower Sorbian (DE--D…