Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation

Authors: Limisiewicz, Tomasz, Mareček, David, Musil, Tomáš

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2501.10150

Transforming Hidden States into Binary Semantic Features

Authors: Musil, Tomáš, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2409.19813

Debiasing Algorithm through Model Adaptation

Authors: Limisiewicz, Tomasz, Mareček, David, Musil, Tomáš

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2310.18913

Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation

Authors: Iluz, Bar, Limisiewicz, Tomasz, Stanovsky, Gabriel, Mareček, David

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2309.12491

Closing the loop: Autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments

Authors: Pithan, Linus, Starostin, Vladimir, Mareček, David, Petersdorf, Lukas, Völter, Constantin, Munteanu, Valentin, Jankowski, Maciej, Konovalov, Oleg, Gerlach, Alexander, Hinderhofer, Alexander, Murphy, Bridget, Kowarik, Stefan, Schreiber, Frank

Subject Terms: Physics - Data Analysis, Statistics and Probability, Condensed Matter - Materials Science, Computer Science - Machine Learning, Physics - Applied Physics

Access URL: http://arxiv.org/abs/2306.11899

Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages

Authors: Limisiewicz, Tomasz, Balhar, Jiří, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2305.17179

Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test

Authors: Musil, Tomáš, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2212.09580

Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information

Authors: Limisiewicz, Tomasz, Mareček, David

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2206.10744

This result is not displayed to guests.
Login for full access.

Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes

Authors: Limisiewicz, Tomasz, Mareček, David

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2109.04921

THEaiTRE 1.0: Interactive generation of theatre play scripts

Authors: Rosa, Rudolf, Musil, Tomáš, Dušek, Ondřej, Jurko, Dominik, Schmidtová, Patrícia, Mareček, David, Bojar, Ondřej, Kocmi, Tom, Hrbek, Daniel, Košťák, David, Kinská, Martina, Nováková, Marie, Doležal, Josef, Vosecká, Klára, Studeník, Tomáš, Žabka, Petr

Source: Proc. Text2Story (2021) 71-76

Subject Terms: Computer Science - Computation and Language, Computer Science - Human-Computer Interaction

Access URL: http://arxiv.org/abs/2102.08892

Introducing Orthogonal Constraint in Structural Probes

Authors: Limisiewicz, Tomasz, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2012.15228

Syntax Representation in Word Embeddings and Neural Networks -- A Survey

Authors: Limisiewicz, Tomasz, Mareček, David

Source: Proceedings of the 20th Conference ITAT 2020: Automata, Formal and Natural Languages Workshop

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2010.01063

Measuring Memorization Effect in Word-Level Neural Networks Probing

Authors: Rosa, Rudolf, Musil, Tomáš, Mareček, David

Source: LNCS 12284, TSD (2020) 180-188

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2006.16082

THEaiTRE: Artificial Intelligence to Write a Theatre Play

Authors: Rosa, Rudolf, Dušek, Ondřej, Kocmi, Tom, Mareček, David, Musil, Tomáš, Schmidtová, Patrícia, Jurko, Dominik, Bojar, Ondřej, Hrbek, Daniel, Košťák, David, Kinská, Martina, Doležal, Josef, Vosecká, Klára

Source: Proc. AI4Narratives (2020) 9-13

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2006.14668

Universal Dependencies according to BERT: both more specific and more general

Authors: Limisiewicz, Tomasz, Rosa, Rudolf, Mareček, David

Source: Findings of the Association for Computational Linguistics: EMNLP 2020

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2004.14620

Inducing Syntactic Trees from BERT Representations

Authors: Rosa, Rudolf, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/1906.11511

Derivational Morphological Relations in Word Embeddings

Authors: Musil, Tomáš, Vidra, Jonáš, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/1906.02510

From Balustrades to Pierre Vinken: Looking for Syntax in Transformer Self-Attentions

Authors: Mareček, David, Rosa, Rudolf

Subject Terms: Computer Science - Computation and Language, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/1906.01958

Input Combination Strategies for Multi-Source Transformer Decoder

Authors: Libovický, Jindřich, Helcl, Jindřich, Mareček, David

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/1811.04716