| 2026 | ACL | Reasoning Gets Harder for LLMs Inside A Dialogue. | Ivan Kartc, Mateusz Lango, Ondrej Dusek |
| 2026 | ACL | Modular Monolingual Adaptation using Pretrained Language Models. | Nalin Kumar, Ondrej Dusek |
| 2026 | ACL | One-step Nonautoregressive Natural Language Generation with Shortcut Flow Matching Models. | Jedrzej Warczynski, Ondrej Dusek, Mateusz Lango |
| 2026 | LREC | HotelCheckSpan: A Benchmark Dataset for LLM Faithfulness. | Patricia Schmidtov, Ondrej Dusek, Saad Mahamood |
| 2025 | EMNLP | Can Large Language Models Personalize Dialogues to Generational Styles? | Pier Felice Balestrucci, Ondrej Dusek, Luca Anselma, Alessandro Mazzei |
| 2025 | EMNLP | SRS-Stories: Vocabulary-constrained multilingual story generation for language learning. | Wiktor Kamzela, Mateusz Lango, Ondrej Dusek |
| 2025 | EMNLP | LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators. | Mateusz Lango, Ondrej Dusek |
| 2025 | EMNLP | Real-World Summarization: When Evaluation Reaches Its Limits. | Patrcia Schmidtov, Ondrej Dusek, Saad Mahamood |
| 2025 | INLG | OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs. | Ivan Kartc, Mateusz Lango, Ondrej Dusek |
| 2025 | INLG | When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition. | Karen Jia-Hui Li, Simone Balloccu, Ondrej Dusek, Ehud Reiter |
| 2025 | INLG | FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation. | Kristna Onderkov, Ondrej Pltek, Zdenek Kasner, Ondrej Dusek |
| 2025 | INLG | Do My Eyes Deceive Me? A Survey of Human Evaluations of Hallucinations in NLG. | Patrcia Schmidtov, Eduardo Cal, Simone Balloccu, Dimitra Gkatzia, Rudali Huidrom, Mateusz Lango, Fahime Same, Vilm Zouhar, Saad Mahamood, Ondrej Dusek |
| 2025 | INLG | How (un)faithful are explainable LLM-based NLG metrics? | Alex Terentowicz, Mateusz Lango, Ondrej Dusek |
| 2025 | NAACL | Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics? | Sourabrata Mukherjee, Atul Kr. Ojha, John Philip McCrae, Ondrej Dusek |
| 2024 | ACL | Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation. | Zdenek Kasner, Ondrej Dusek |
| 2024 | EACL | Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs. | Simone Balloccu, Patrcia Schmidtov, Mateusz Lango, Ondrej Dusek |
| 2024 | EMNLP | Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-AI collaboration. | Simone Balloccu, Ehud Reiter, Karen Li, Rafael Sargsyan, Vivek Kumar, Diego Reforgiato Recupero, Daniele Riboni, Ondrej Dusek |
| 2024 | EMNLP | Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach. | Adam Wojciechowski, Mateusz Lango, Ondrej Dusek |
| 2024 | INLG | factgenie: A Framework for Span-based Evaluation of Generated Texts. | Zdenek Kasner, Ondrej Pltek, Patrcia Schmidtov, Simone Balloccu, Ondrej Dusek |
| 2024 | INLG | Multilingual Text Style Transfer: Datasets & Models for Indian Languages. | Sourabrata Mukherjee, Atul Kr. Ojha, Akanksha Bansal, Deepak Alok, John P. McCrae, Ondrej Dusek |
| 2024 | INLG | Are Large Language Models Actually Good at Text Style Transfer? | Sourabrata Mukherjee, Atul Kr. Ojha, Ondrej Dusek |
| 2024 | INLG | Automatic Metrics in Natural Language Generation: A survey of Current Evaluation Practices. | Patrcia Schmidtov, Saad Mahamood, Simone Balloccu, Ondrej Dusek, Albert Gatt, Dimitra Gkatzia, David M. Howcroft, Ondrej Pltek, Adarsa Sivaprasad |
| 2024 | INLG | Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems. | Jedrzej Warczynski, Mateusz Lango, Ondrej Dusek |
| 2024 | NAACL | LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems. | Nalin Kumar, Ondrej Dusek |
| 2023 | ACL | TabGenie: A Toolkit for Table-to-Text Generation. | Zdenek Kasner, Ekaterina Garanina, Ondrej Pltek, Ondrej Dusek |
| 2023 | EACL | Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models. | Zdenek Kasner, Ioannis Konstas, Ondrej Dusek |
| 2023 | EACL | Polite Chatbot: A Text Style Transfer Application. | Sourabrata Mukherjee, Vojtech Hudecek, Ondrej Dusek |
| 2023 | EMNLP | Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation. | Mateusz Lango, Ondrej Dusek |
| 2023 | INLG | Tackling Hallucinations in Neural Chart Summarization. | Saad Obaid ul Islam, Iza Skrjanec, Ondrej Dusek, Vera Demberg |
| 2023 | INLG | Leveraging Low-resource Parallel Data for Text Style Transfer. | Sourabrata Mukherjee, Ondrej Dusek |
| 2023 | SIGdial | Are Large Language Models All You Need for Task-Oriented Dialogue? | Vojtech Hudecek, Ondrej Dusek |
| 2022 | ACL | Neural Pipeline for Zero-Shot Data-to-Text Generation. | Zdenek Kasner, Ondrej Dusek |
| 2022 | IJCNLP | Learning Interpretable Latent Dialogue Actions With Less Supervision. | Vojtech Hudecek, Ondrej Dusek |
| 2022 | LREC | A Unifying View On Task-oriented Dialogue Annotation. | Vojtech Hudecek, Lon-Paul Schaub, Daniel Stancl, Patrick Paroubek, Ondrej Dusek |
| 2022 | SIGIR | The Seventh Workshop on Search-Oriented Conversational Artificial Intelligence (SCAI'22). | Gustavo Penha, Svitlana Vakulenko, Ondrej Dusek, Leigh Clark, Vaishali Pal, Vaibhav Adlakha |
| 2022 | SIGdial | AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog. | Toms Nekvinda, Ondrej Dusek |
| 2021 | ACL | Discovering Dialogue Slots with Weak Supervision. | Vojtech Hudecek, Ondrej Dusek, Zhou Yu |
| 2021 | ACL | AggGen: Ordering and Aggregating while Generating. | Xinnuo Xu, Ondrej Dusek, Verena Rieser, Ioannis Konstas |
| 2021 | ECIR | THEaiTRE 1.0: Interactive Generation of Theatre Play Scripts. | Rudolf Rosa, Toms Musil, Ondrej Dusek, Dominik Jurko, Patrcia Schmidtov, David Marecek, Ondrej Bojar, Tom Kocmi, Daniel Hrbek, David Kostk, Martina Kinsk, Marie Novkov, Josef Dolezal, Klra Voseck, Toms Studenk, Petr Zabka |
| 2021 | EMNLP | MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization. | Xinnuo Xu, Ondrej Dusek, Shashi Narayan, Verena Rieser, Ioannis Konstas |
| 2021 | INLG | Text-in-Context: Token-Level Error Detection for Table-to-Text Generation. | Zdenek Kasner, Simon Mille, Ondrej Dusek |
| 2021 | INLG | Underreporting of errors in NLG output, and what to do about it. | Emiel van Miltenburg, Miruna-Adriana Clinciu, Ondrej Dusek, Dimitra Gkatzia, Stephanie Inglis, Leo Leppnen, Saad Mahamood, Emma Manning, Stephanie Schoch, Craig Thomson, Luou Wen |
| 2020 | ACL | Fact-based Content Weighting for Evaluating Abstractive Summarisation. | Xinnuo Xu, Ondrej Dusek, Jingyi Li, Verena Rieser, Ioannis Konstas |
| 2020 | IJCAI | THEaiTRE: Artificial Intelligence to Write a Theatre Play. | Rudolf Rosa, Ondrej Dusek, Tom Kocmi, David Marecek, Toms Musil, Patrcia Schmidtov, Dominik Jurko, Ondrej Bojar, Daniel Hrbek, David Kostk, Martina Kinsk, Josef Dolezal, Klra Voseck |
| 2020 | INLG | Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference. | Ondrej Dusek, Zdenek Kasner |
| 2020 | INLG | Data-to-Text Generation with Iterative Text Editing. | Zdenek Kasner, Ondrej Dusek |
| 2020 | Interspeech | One Model, Many Languages: Meta-Learning for Multilingual Text-to-Speech. | Toms Nekvinda, Ondrej Dusek |
| 2020 | Interspeech | SpeedySpeech: Efficient Neural Speech Synthesis. | Jan Vainer, Ondrej Dusek |
| 2019 | INLG | Semantic Noise Matters for Neural Natural Language Generation. | Ondrej Dusek, David M. Howcroft, Verena Rieser |
| 2019 | INLG | Neural Generation for Czech: Data and Baselines. | Ondrej Dusek, Filip Jurccek |
| 2019 | INLG | Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking). | Ondrej Dusek, Karin Sevegnani, Ioannis Konstas, Verena Rieser |
| 2019 | SIGdial | User Evaluation of a Multi-dimensional Statistical Dialogue System. | Simon Keizer, Ondrej Dusek, Xingkun Liu, Verena Rieser |
| 2018 | EMNLP | A Knowledge-Grounded Multimodal Search-Based Conversational Agent. | Shubham Agarwal, Ondrej Dusek, Ioannis Konstas, Verena Rieser |
| 2018 | EMNLP | Neural Response Ranking for Social Conversation: A Data-Efficient Approach. | Igor Shalyminov, Ondrej Dusek, Oliver Lemon |
| 2018 | EMNLP | Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity. | Xinnuo Xu, Ondrej Dusek, Ioannis Konstas, Verena Rieser |
| 2018 | INLG | Improving Context Modelling in Multimodal Dialogue Generation. | Shubham Agarwal, Ondrej Dusek, Ioannis Konstas, Verena Rieser |
| 2018 | INLG | Findings of the E2E NLG Challenge. | Ondrej Dusek, Jekaterina Novikova, Verena Rieser |
| 2018 | NAACL | RankME: Reliable Human Ratings for Natural Language Generation. | Jekaterina Novikova, Ondrej Dusek, Verena Rieser |
| 2017 | EMNLP | Why We Need New Evaluation Metrics for NLG. | Jekaterina Novikova, Ondrej Dusek, Amanda Cercas Curry, Verena Rieser |
| 2017 | SIGdial | The E2E Dataset: New Challenges For End-to-End Generation. | Jekaterina Novikova, Ondrej Dusek, Verena Rieser |
| 2016 | ACL | Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings. | Ondrej Dusek, Filip Jurccek |
| 2016 | SIGdial | A Context-aware Natural Language Generator for Dialogue Systems. | Ondrej Dusek, Filip Jurccek |
| 2015 | ACL | Training a Natural Language Generator From Unaligned Data. | Ondrej Dusek, Filip Jurccek |
| 2014 | LREC | Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license. | Matej Korvas, Ondrej Pltek, Ondrej Dusek, Luks Zilka, Filip Jurccek |
| 2014 | LREC | Multilingual Test Sets for Machine Translation of Search Queries for Cross-Lingual Information Retrieval in the Medical Domain. | Zdenka Uresov, Jan Hajic, Pavel Pecina, Ondrej Dusek |
| 2014 | SIGdial | Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users. | Ondrej Dusek, Ondrej Pltek, Luks Zilka, Filip Jurccek |
| 2013 | ACL | Robust multilingual statistical morphological generation models. | Ondrej Dusek, Filip Jurccek |
| 2012 | LREC | The Joy of Parallelism with CzEng 1.0. | Ondrej Bojar, Zdenek Zabokrtsk, Ondrej Dusek, Petra Galusckov, Martin Majlis, David Marecek, Jir Marsk, Michal Novk, Martin Popel, Ales Tamchyna |