Zdeněk Kasner
Main Research Interests
- Low-Resource Data-to-Text Generation
- Evaluation of Natural Language Generation
- Reasoning of Large Language Models
Projects
- Principal Investigator
- 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)
- NPFL140 – Large Language Models (23/24, 24/25)
- 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)
Theses and projects
Active
- MSc. - Danil Semin – Span Labeling with Decoder-Only Large Language Models
- MSc. - Anna Sajdoková – Design and Evaluation of a Retrieval-Augmented Generation System for Czech
- Research proj. - Filip Rechtorík – Generating Descriptions of Time Series Data
- BSc. - Tymur Kotkov – Methods for Updating Knowledge in Code Generation Models
Defended
- BSc. - Václav Hrouda – Automatizace generování popisů produktů pomocí neuronových jazykových modelů (2024)
- BSc. - Katarina Bucková – Story Generation Using Dynamic Text Infilling (2023)
Selected Bibliography
- Google Scholar
- ORCID: 0000-0002-5753-5538
- Scopus ID: 57219694109
- Researcher ID: HPD-5993-2023
Papers
- Large Language Models as Span Annotators (Electronic). In: ArXiv.org Computing Research Repository, ISSN 2331-8422 (url)
- FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation. In: Proceedings of the 18th International Natural Language Generation Conference, pp. 108-121, Association for Computational Linguistics, Kerrville, TX, USA, ISBN 979-8-89176-321-0 (url, bibtex)
- Teaching LLMs at Charles University: Assignments and Activities. In: The Sixth Workshop on Teaching NLP: Proceedings of the Workshop, pp. 69-72, Association for Computational Linguistics, Kerrville, TX, USA, ISBN 979-8-89176-134-6 (url, local PDF, local PDF, bibtex)
- Data-to-Text Generation with Neural Language Models (PhD thesis). In: (url, bibtex)
- Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12045-12072, Association for Computational Linguistics, Kerrville, TX, USA, ISBN 979-8-89176-094-3 (url, bibtex)
- factgenie: A Framework for Span-based Evaluation of Generated Texts. In: Proceedings of the 17th International Natural Language Generation Conference: System Demonstrations, pp. 13-15, Association for Computational Linguistics, Kerrville, TX, USA, ISBN 979-8-89176-123-0 (url, bibtex)
- WebLINX: Real-World Website Navigation with Multi-Turn Dialogue. In: Proceedings of the 41st International Conference on Machine Learning, pp. 1-50, Proceedings of Machine Learning Research (PMLR), San Diego, USA, ISBN 9798331302238 (url, bibtex)
- 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)
- 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, Kerrville, TX, USA, ISBN 978-1-959429-44-9 (url, bibtex)
- 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)
- 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)
- 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)
- 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)
- 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)
- 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)
- 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)
- 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