Lukas Edman

25 papers A* 1C 1Misc 1Journal 12Unranked 10
YearRankTypeTitle / Venue / Authors
2025 — conf
EXECUTE: A Multilingual Benchmark for LLM Token Understanding.
ACL (Findings)
Lukas Edman, Helmut Schmid, Alexander Fraser
2025 J jnl
EXECUTE: A Multilingual Benchmark for LLM Token Understanding.
CoRR
Lukas Edman, Helmut Schmid, Alexander Fraser
2025 J jnl
Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs.
CoRR
Lukas Edman, Alexander Fraser
2025 Misc conf
Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models Using Set Encoding.
KI
Lukas Kinder, Lukas Edman, Alexander Fraser, Tobias Käfer
2025 — conf
Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding.
ACL (1)
Lukas Kinder, Lukas Edman, Alexander Fraser, Tobias Käfer
2024 J jnl
Are BabyLMs Second Language Learners?
CoRR
Lukas Edman, Lisa Bylinina, Faeze Ghorbanpour, Alexander Fraser
2024 J jnl
Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation.
Trans. Assoc. Comput. Linguistics
Lukas Edman, Gabriele Sarti, Antonio Toral, Gertjan van Noord, Arianna Bisazza
2024 A* conf
CUTE: Measuring LLMs' Understanding of Their Tokens.
EMNLP
Lukas Edman, Helmut Schmid, Alexander Fraser
2024 J jnl
CUTE: Measuring LLMs' Understanding of Their Tokens.
CoRR
Lukas Edman, Helmut Schmid, Alexander Fraser
2023 J jnl
Are Character-level Translations Worth the Wait? An Extensive Comparison of Character- and Subword-level Models for Machine Translation.
CoRR
Lukas Edman, Antonio Toral, Gertjan van Noord
2023 — conf
LCT-1 at SemEval-2023 Task 10: Pre-training and Multi-task Learning for Sexism Detection and Classification.
SemEval@ACL
Konstantin Chernyshev, Ekaterina Garanina, Duygu Bayram, Qiankun Zheng, Lukas Edman
2023 J jnl
LCT-1 at SemEval-2023 Task 10: Pre-training and Multi-task Learning for Sexism Detection and Classification.
CoRR
Konstantin Chernyshev, Ekaterina Garanina, Duygu Bayram, Qiankun Zheng, Lukas Edman
2023 J jnl
Too Much Information: Keeping Training Simple for BabyLMs.
CoRR
Lukas Edman, Lisa Bylinina
2022 J jnl
Patching Leaks in the Charformer for Efficient Character-Level Generation.
CoRR
Lukas Edman, Antonio Toral, Gertjan van Noord
2022 — conf
RUG-1-Pegasussers at SemEval-2022 Task 3: Data Generation Methods to Improve Recognizing Appropriate Taxonomic Word Relations.
SemEval@NAACL
Wessel Poelman, Gijs Danoe, Esther Ploeger, Frank van den Berg, Tommaso Caselli, Lukas Edman
2022 — conf
Subword-Delimited Downsampling for Better Character-Level Translation.
EMNLP (Findings)
Lukas Edman, Antonio Toral, Gertjan van Noord
2022 J jnl
Subword-Delimited Downsampling for Better Character-Level Translation.
CoRR
Lukas Edman, Antonio Toral, Gertjan van Noord
2022 J jnl
The Importance of Context in Very Low Resource Language Modeling.
CoRR
Lukas Edman, Antonio Toral, Gertjan van Noord
2021 — conf
The Importance of Context in Very Low Resource Language Modeling.
ICON
Lukas Edman, Antonio Toral, Gertjan van Noord
2021 — conf
Unsupervised Translation of German-Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language.
WMT@EMNLP
Lukas Edman, Ahmet Üstün, Antonio Toral, Gertjan van Noord
2021 J jnl
Unsupervised Translation of German-Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language.
CoRR
Lukas Edman, Ahmet Üstün, Antonio Toral, Gertjan van Noord
2020 — conf
Data Selection for Unsupervised Translation of German-Upper Sorbian.
WMT@EMNLP
Lukas Edman, Antonio Toral, Gertjan van Noord
2020 C conf
Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated Solution.
EAMT
Lukas Edman, Antonio Toral, Gertjan van Noord
2020 — conf
Machine Translation for English-Inuktitut with Segmentation, Data Acquisition and Pre-Training.
WMT@EMNLP
Christian Roest, Lukas Edman, Gosse Minnema, Kevin Kelly, Jennifer Spenader, Antonio Toral
2019 — conf
Neural Machine Translation for English-Kazakh with Morphological Segmentation and Synthetic Data.
WMT (2)
Antonio Toral, Lukas Edman, Galiya Yeshmagambetova, Jennifer Spenader