Published in ACL, 2024
Recommended citation: Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia and Luke Zettlemoyer (2024). "MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling"ACL 2024. https://arxiv.org/pdf/2403.10691
Published in ICLR, 2024
Recommended citation: Limisiewicz, Tomasz and Mareček, David and Musil, Tomáš (2024). "Debiasing Algorithm through Model Adaptation" ICLR 2024. https://arxiv.org/pdf/2310.18913.pdf
Published in IJCNLP and AACL, 2023
Recommended citation: Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky, and David Mareček (2023). "Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation" IJCNLP and AACL 2023. https://aclanthology.org/2023.ijcnlp-main.57.pdf
Published in Findings of ACL, 2023
Recommended citation: Tomasz Limisiewicz, Jiří Balhar, and David Mareček (2023). "Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages"ACL Findings 2023. https://aclanthology.org/2023.findings-acl.350.pdf
Published in NAACL (Awarded Outstanding Paper 🥳), 2022
Recommended citation: Dan Malkin, Tomasz Limisiewicz, and Gabriel Stanovsky (2022). "A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank"NAACL 2022. https://aclanthology.org/2022.naacl-main.361.pdf
Published in Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP), 2022
Recommended citation: Tomasz Limisiewicz and David Mareček (2022). "Don’t Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information"GeBNLP 2022. https://aclanthology.org/2022.gebnlp-1.3.pdf
Published in Conference on Empirical Methods in Natural Language Processing, 2021
Recommended citation: Limisiewicz, Tomasz and Mareček, David (2021). "Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes" EMNLP 2021. https://aclanthology.org/2021.emnlp-main.376.pdf
Published in Annual Meeting of the Association for Computational Linguistics, 2021
Recommended citation: Limisiewicz, Tomasz and Mareček, David (2021). "Introducing Orthogonal Constraint in Structural Probes" ACL 2021. https://aclanthology.org/2021.acl-long.36.pdf
Published in Conference Information Technologies - Applications and Theory, 2020
Recommended citation: Limisiewicz, Tomasz and Mareček, David (2020). "Syntax Representation in Word Embeddings and Neural Networks – A Survey" ITAT 2020. http://ceur-ws.org/Vol-2718/paper16.pdf
Published in Findings of EMNLP, 2020
Recommended citation: Limisiewicz, Tomasz and Mareček, David and Rosa, Rudolf (2020). "Universal Dependencies According to BERT: Both More Specific and More General" EMNLP Findings 2020. https://aclanthology.org/2020.findings-emnlp.245.pdf
Published in Conference on Machine Translation, 2020
Recommended citation: Kocmi, Tom and Limisiewicz, Tomasz and Stanovsky, Gabriel (2020). "Gender Coreference and Bias Evaluation at WMT 2020" WMT 2020. https://aclanthology.org/2020.wmt-1.39.pdf