Zdeněk Kasner

Main Research Interests

• Low-Resource Data-to-Text Generation
• Evaluation of Natural Language Generation
• Story Generation
• Reasoning and Interpretability of Large Language Models

Projects

• Principal Investigator
  • 2020-2022: Domain Adaptation for Natural Language Generation (GAUK 140320)
• ​Participant
  • 2023-now: NG-NLG (European Research Council Grant Agreement No. 101039303)
  • 2021-2022: Apple NLU Research Grant for Heriot-Watt University and Charles University
  • 2019-2021: NaMuDDiS (PRIMUS/19/SCI/10)

Curriculum Vitae

• Link to my full Curriculum Vitae (PDF).

Teaching

Courses

• List of my current courses (with SIS login only)
   
• NPFL129 – Machine Learning for Greenhorns (23/24) 
• NPFL099 – Statistical Dialogue Systems (22/23)
• NSWI177 – Introduction to Linux (21/22)
• NPRG062 – Introduction to Algorithms + NPRG030 – Programming I (20/21, online)

Bachelor Theses

• Katarina Bucková – Story Generation Using Dynamic Text Infilling
• Václav Hrouda – Automatizace generování popisů produktů pomocí neuronových jazykových modelů

 

Selected Bibliography

• Google Scholar
• ORCID: 0000-0002-5753-5538
• Scopus ID: 57219694109
• Researcher ID: HPD-5993-2023

Papers

1. Zdeněk Kasner, Ekaterina Garanina, Ondřej Plátek, Ondřej Dušek (2023): TabGenie: A Toolkit for Table-to-Text Generation. In: Proceedings of 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 444-455, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-941643-00-6 (url, bibtex)
2. Zdeněk Kasner, Ioannis Konstas, Ondřej Dušek (2023): Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models. In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2398-2415, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-959429-44-9 (url, bibtex)
3. Rudali Huidrom, Ondřej Dušek, Zdeněk Kasner, Thiago Castro Ferreira, Anya Belz (2022): Two Reproductions of a Human-Assessed Comparative Evaluation of a Semantic Error Detection System. In: Proceedings of the 15th International Conference on Natural Language Generation: Generation Challenges, pp. 52-61, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-955917-60-5 (url, local PDF, bibtex)
4. Zdeněk Kasner, Ondřej Dušek (2022): Neural Pipeline for Zero-Shot Data-to-Text Generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: ACL 2022, pp. 3914-3932, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-955917-21-6 (url, bibtex)
5. Sourabrata Mukherjee, Zdeněk Kasner, Ondřej Dušek (2022): Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising. In: 25th International Conference on Text, Speech and Dialogue, pp. 172-186, Springer, Cham, Switzerland, ISBN 978-3-031-16269-5 (url, bibtex)
6. Zdeněk Kasner, Simon Mille, Ondřej Dušek (2021): Text-in-Context: Token-Level Error Detection for Table-to-Text Generation. In: Proceedings of the 14th International Conference on Natural Language Generation (INLG 2021), pp. 259-265, Association for Computational Linguistics, Stroudsburgh, PA, USA, ISBN 978-1-954085-51-0 (pdf, bibtex)
7. Ondřej Dušek, Zdeněk Kasner (2020): Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference. In: Proceedings of the 13th International Conference on Natural Language Generation (INLG 2020), pp. 131-137, Association for Computational Linguistics, Stroudsburgh, PA, USA, ISBN 978-1-952148-54-5 (url, bibtex)
8. Zdeněk Kasner, Ondřej Dušek (2020): Train Hard, Finetune Easy: Multilingual Denoising for RDF-to-Text Generation. In: Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+), pp. 171-176, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-952148-59-0 (url, bibtex)
9. Zdeněk Kasner, Ondřej Dušek (2020): Data-to-Text Generation with Iterative Text Editing. In: Proceedings of the 13th International Conference on Natural Language Generation (INLG 2020), pp. 60-67, Association for Computational Linguistics, Stroudsburgh, PA, USA, ISBN 978-1-952148-54-5 (url, bibtex)
10. Jindřich Libovický, Zdeněk Kasner, Jindřich Helcl, Ondřej Dušek (2020): Expand and Filter: CUNI and LMU Systems for the WNGT 2020 Duolingo Shared Task. In: Proceedings of the Fourth Workshop on Neural Generation and Translation, pp. 153-160, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-952148-17-0 (url, local PDF, bibtex)

(the list is exported automatically from Biblio)

Theses

• Master Thesis: Incorporating Language Models into Non-autoregressive Neural Machine Translation
• Bachelor Thesis: Flow-Based Classification of Devices in Computer Networks