Ondrej Dusek
I'm an Assistant Professor at Charles University, Prague, working on various aspects of neural text generation, with focus on dialogue systems and factual accuracy. I previously did research at Heriot-Watt University in Edinburgh, working on natural language generation evaluation and improvement. My work focuses on making language generation systems more reliable and truthful while maintaining fluent outputs.
I lead research on data-to-text generation, dialogue response generation, and text style transfer. I'm particularly interested in methods for controlling generation output and ensuring semantic accuracy. I've contributed to creating several widely used datasets and evaluation methods, such as the E2E NLG Challenge dataset and automatic semantic accuracy metrics.
Publications
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
Anya Belz, Craig Thomson, Ehud Reiter, Gavin Abercrombie, J. Alonso-Moral, Mohammad Arvan, J. Cheung, Mark Cieliebak, Elizabeth Clark, K. V. Deemter, Tanvi Dinkar, Ondrej Dusek, Steffen Eger, Qixiang Fang, Albert Gatt, Dimitra Gkatzia, Javier Gonz'alez-Corbelle, Dirk Hovy, Manuela Hurlimann, Takumi Ito, John D. Kelleher, Filip Klubicka, Huiyuan Lai, Chris van der Lee, Emiel van Miltenburg, Yiru Li, Saad Mahamood, Margot Mieskes, M. Nissim, Natalie Parde, Ondvrej Pl'atek, Verena Rieser, Pablo Romero, Joel R. Tetreault, Antonio Toral, Xiao-Yi Wan, L. Wanner, Lewis J. Watson, Diyi Yang
First Workshop on Insights from Negative Results in NLP 2023
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, A. Papangelis, Aman Madaan, Angelina McMillan-Major, Anna Shvets, Ashish Upadhyay, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir R. Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh D. Dhole, Khyathi Raghavi Chandu, Leonardo F. R. Ribeiro, Lewis Tunstall, Li Zhang, Mahima Pushkarna, Mathias Creutz, Michael White, Mihir Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, P. Liang, Pawan Sasanka Ammanamanchi, Qinqin Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, S. vStajner, Sébastien Montella, Shailza, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin P. Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, V. Tsai, Yacine Jernite, Yi Xu, Yisi Sang, Yixin Liu, Yufang Hou
Conference on Empirical Methods in Natural Language Processing 2022
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann, Aadesh Gupta, Zhenhao Li, Saad Mahamood, Abinaya Mahendiran, Simon Mille, Ashish Srivastava, Samson Tan, Tongshuang Sherry Wu, Jascha Narain Sohl-Dickstein, Jinho D. Choi, E. Hovy, Ondrej Dusek, Sebastian Ruder, Sajant Anand, Nagender Aneja, Rabin Banjade, Lisa Barthe, Hanna Behnke, Ian Berlot-Attwell, Connor Boyle, C. Brun, Marco Antonio Sobrevilla Cabezudo, Samuel Cahyawijaya, E. Chapuis, Wanxiang Che, Mukund Choudhary, C. Clauss, Pierre Colombo, Filip Cornell, Gautier Dagan, M. Das, Tanay Dixit, Thomas Dopierre, Paul-Alexis Dray, Suchitra Dubey, Tatiana Ekeinhor, Marco Di Giovanni, Rishabh Gupta, Louanes Hamla, Sanghyun Han, Fabrice Harel-Canada, A. Honoré, Ishan Jindal, Przemyslaw K. Joniak, D. Kleyko, Venelin Kovatchev, Kalpesh Krishna, Ashutosh Kumar, Stefan Langer, S. Lee, Corey J. Levinson, H.-J. Liang, Kaizhao Liang, Zhexiong Liu, Andrey Lukyanenko, Vukosi Marivate, Gerard de Melo, Simon Meoni, Maxime Meyer, Afnan Mir, N. Moosavi, Niklas Muennighoff, Timothy Sum Hon Mun, Kenton W. Murray, Marcin Namysl, Maria Obedkova, Priti Oli, Nivranshu Pasricha, Jan Pfister, Richard Plant, Vinay Uday Prabhu, V. Pais, Libo Qin, Shahab Raji, P. Rajpoot, Vikas Raunak, Roy Rinberg, N. Roberts, Juan Diego Rodriguez, Claude Roux, S. VasconcellosP.H., Ananya B. Sai, Robin M. Schmidt, Thomas Scialom, T. Sefara, Saqib Nizam Shamsi, Xudong Shen, Haoyue Shi, Y. Shi, Anna Shvets, Nick Siegel, Damien Sileo, Jamie Simon, Chandan Singh, Roman Sitelew, P. Soni, Taylor Sorensen, William Soto Martinez, Aman Srivastava, KV Aditya Srivatsa, Tony Sun, T. MukundVarma, A. Tabassum, Fiona Anting Tan, Ryan Teehan, Monalisa Tiwari, M. Tolkiehn, Athena Wang, Zijian Wang, Gloria Xinyue Wang, Zijie J. Wang, Fuxuan Wei, Bryan Wilie, Genta Indra Winata, Xinyi Wu, Witold Wydmański, Tianbao Xie, Usama Yaseen, M. Yee, Jing Zhang, Yue Zhang
NEJLT 2021
Report on the 6th workshop on search-oriented conversational AI (SCAI 2021)
S. Vakulenko, Ondrej Dusek
SIGIR Forum 2021
THEaiTRE 1.0: Interactive Generation of Theatre Play Scripts
Rudolf Rosa, Tomáš Musil, Ondrej Dusek, Dominik Jurko, Patr'icia Schmidtov'a, David Marevcek, Ondrej Bojar, Tom Kocmi, Daniel Hrbek, David Kovsvt'ak, Martina Kinsk'a, Marie Nov'akov'a, Josef Dolevzal, Kl'ara Voseck'a, Tom'avs Studen'ik, Petr vZabka
Text2Story@ECIR 2021
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Sebastian Gehrmann, Tosin P. Adewumi, Karmanya Aggarwal, Pawan Sasanka Ammanamanchi, Aremu Anuoluwapo, Antoine Bosselut, Khyathi Raghavi Chandu, Miruna Clinciu, Dipanjan Das, Kaustubh D. Dhole, Wanyu Du, Esin Durmus, Ondrej Dusek, Chris C. Emezue, Varun Prashant Gangal, Cristina Garbacea, Tatsunori B. Hashimoto, Yufang Hou, Yacine Jernite, Harsh Jhamtani, Yangfeng Ji, Shailza Jolly, Mihir Kale, Dhruv Kumar, Faisal Ladhak, Aman Madaan, Mounica Maddela, Khyati Mahajan, Saad Mahamood, Bodhisattwa Prasad Majumder, Pedro Henrique Martins, Angelina McMillan-Major, Simon Mille, Emiel van Miltenburg, Moin Nadeem, Shashi Narayan, Vitaly Nikolaev, Andre Niyongabo Rubungo, Salomey Osei, Ankur P. Parikh, Laura Perez-Beltrachini, Niranjan Rao, Vikas Raunak, Juan Diego Rodriguez, Sashank Santhanam, João Sedoc, Thibault Sellam, Samira Shaikh, Anastasia Shimorina, Marco Antonio Sobrevilla Cabezudo, Hendrik Strobelt, Nishant Subramani, Wei Xu, Diyi Yang, Akhila Yerukola, Jiawei Zhou
IEEE Games Entertainment Media Conference 2021
Fact-based Content Weighting for Evaluating Abstractive Summarisation
Xinnuo Xu, Ondrej Dusek, Jingyi Li, Verena Rieser, Ioannis Konstas
Annual Meeting of the Association for Computational Linguistics 2020
Novel Methods for Natural Language Generation in Spoken Dialogue Systems
Ondrej Dusek
Czech restaurant information dataset for NLG
Ondrej Dusek, Filip Jurcícek, Josef Dvorak, Petra Grycová, M. Hejda, J. Olivová, Michal Starý, Eva Štichová
Verb sense disambiguation in Machine Translation
R. Sudarikov, Ondrej Dusek, Martin Holub, Ondrej Bojar, Vincent Kríz
HyTra@COLING 2016
Moses & Treex Hybrid MT Systems Bestiary
Rudolf Rosa, M. Popel, Ondrej Bojar, D. Mareček, Ondrej Dusek
Deep Machine Translation Workshop 2016
CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered
Ondrej Bojar, Ondrej Dusek, Tom Kocmi, Jindřich Libovický, M. Novák, M. Popel, R. Sudarikov, Dusan Varis
International Conference on Text, Speech and Dialogue 2016
Vystadial 2016 – Czech data
Ondřej Plátek, Ondrej Dusek, Filip Jurcícek
Alex Context NLG Dataset
Ondrej Dusek, Filip Jurčíček
New Language Pairs in TectoMT
Ondrej Dusek, Luís Manuel dos Santos Gomes, M. Novák, M. Popel, Rudolf Rosa
WMT@EMNLP 2015
Using Parallel Texts and Lexicons for Verbal Word Sense Disambiguation
Ondrej Dusek, Eva Fucíková, Jan Hajic, M. Popel, J. Šindlerová, Zdenka Uresová
International Conference on Dependency Linguistics 2015
Alex: A Statistical Dialogue Systems Framework
Filip Jurcícek, Ondrej Dusek, Ondřej Plátek, Lukás Zilka
International Conference on Text, Speech and Dialogue 2014
A Factored Discriminative Spoken Language Understanding for Spoken Dialogue Systems
Filip Jurcícek, Ondrej Dusek, Ondřej Plátek
International Conference on Text, Speech and Dialogue 2014
HamleDT: Harmonized multi-language dependency treebank
Daniel Zeman, Ondrej Dusek, D. Mareček, M. Popel, L. Ramasamy, J. Stepánek, Z. Žabokrtský, Jan Hajic
Language Resources and Evaluation 2014
Adaptation of machine translation for multilingual information retrieval in the medical domain
Pavel Pecina, Ondrej Dusek, Lorraine Goeuriot, Jan Hajic, Jaroslava Hlavácová, G. Jones, Liadh Kelly, Johannes Leveling, D. Mareček, M. Novák, M. Popel, Rudolf Rosa, A. Tamchyna, Zdenka Uresová
Artif. Intell. Medicine 2014
Verbal Valency Frame Detection and Selection in Czech and English
Ondrej Dusek, Jan Hajic, Zdenka Uresová
EVENTS@ACL 2014
Multilingual Test Sets for Machine Translation of Search Queries for Cross-Lingual Information Retrieval in the Medical Domain
Zdenka Uresová, Jan Hajic, Pavel Pecina, Ondrej Dusek
International Conference on Language Resources and Evaluation 2014
Khresmoi Summary Translation Test Data 1.1
Ondrej Dusek, Jan Hajic, Jaroslava Hlavácová, Pavel Pecina, A. Tamchyna, Zdenka Uresová
Vystadial 2013 – Czech data
Matej Korvas, Ondřej Plátek, Ondrej Dusek, Lukás Zilka, Filip Jurcícek
Vystadial 2013 – English data
Matej Korvas, Ondřej Plátek, Ondrej Dusek, Lukás Zilka, Filip Jurcícek
Vystadial 2013 – scripts
Matej Korvas, Ondřej Plátek, Ondrej Dusek, Lukás Zilka, Filip Jurcícek
Khresmoi Query Translation Test Data 1.0
Pavel Pecina, Ondrej Dusek, Jan Hajic, Zdenka Uresová
Robust multilingual statistical morphological generation models
Ondrej Dusek, Filip Jurcícek
Annual Meeting of the Association for Computational Linguistics 2013
Additional German-Czech reference translations of the WMT'11 test set
Ondrej Bojar, Daniel Zeman, Ondrej Dusek, Jana Břečková, Hana Farkačová, Pavel Grošpic, Kristýna Kačenová, Eva Knechtová, A. Koubová, J. Lukavská, P. Nováková, Jana Petrdlíková
Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors
Rudolf Rosa, Ondrej Dusek, D. Mareček, M. Popel
SSST@ACL 2012
DEPFIX: A System for Automatic Correction of Czech MT Outputs
Rudolf Rosa, D. Mareček, Ondrej Dusek
WMT@NAACL-HLT 2012
Formemes in English-Czech Deep Syntactic MT
Ondrej Dusek, Z. Žabokrtský, M. Popel, Martin Majlis, M. Novák, D. Mareček
WMT@NAACL-HLT 2012
The Joy of Parallelism with CzEng 1.0
Ondrej Bojar, Z. Žabokrtský, Ondrej Dusek, P. Galuscáková, Martin Majlis, D. Mareček, Jirka Marsík, M. Novák, M. Popel, A. Tamchyna
International Conference on Language Resources and Evaluation 2012
Czech-English Parallel Corpus 1.0 (CzEng 1.0)
Ondrej Bojar, Z. Žabokrtský, Ondrej Dusek, P. Galuscáková, Martin Majlis, D. Mareček, Jirka Marsík, M. Novák, M. Popel, A. Tamchyna
VisuaLLM: Easy Web-based Visualization for Neural Language Generation
F. Trebuna, Ondrej Dusek
International Conference on Natural Language Generation 2023
Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems
Jędrzej Warczyński, Mateusz Lango, Ondrej Dusek
International Conference on Natural Language Generation 2024
ReproHum #0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility
Mateusz Lango, Patrícia Schmidtová, Simone Balloccu, Ondrej Dusek
HUMEVAL 2024
Better Translation + Split and Generate for Multilingual RDF-to-Text (WebNLG 2023)
Nalin Kumar, Saad Obaid Ul Islam, Ondrej Dusek
MMNLG 2023
THEaiTRobot: An Interactive Tool for Generating Theatre Play Scripts
Rudolf Rosa, Patrícia Schmidtová, Alisa Zakhtarenko, Ondrej Dusek, Tomáš Musil, D. Mareček, Saad Obaid, Marie Nováková, Klára Vosecká
International Conference on Natural Language Generation 2022
A Unifying View On Task-oriented Dialogue Annotation
Vojtech Hudecek, Léon-Paul Schaub, Daniel Stancl, P. Paroubek, Ondrej Dusek
International Conference on Language Resources and Evaluation 2022
Définition et détection des incohérences du système dans les dialogues orientés tâche. (We present experiments on automatically detecting inconsistent behavior of task-oriented dialogue systems from the context)
Léon-Paul Schaub, Vojtech Hudecek, Daniel Stancl, Ondrej Dusek, Patrick Paroubek
JEPTALNRECITAL 2021
AuGPT: Dialogue with Pre-trained Language Models and Data Augmentation
Jonáš Kulhánek, Vojtech Hudecek, Tomás Nekvinda, Ondrej Dusek
arXiv.org 2021
When a Robot Writes a Play: Automatically Generating a Theatre Play Script
Rudolf Rosa, Tomáš Musil, Ondrej Dusek, Dominik Jurko, Patrícia Schmidtová, D. Mareček, Ondrej Bojar, Tom Kocmi, Daniel Hrbek, Marie Nováková, Josef Doležal, P. Žabka
IEEE Symposium on Artificial Life 2021
Train Hard, Finetune Easy: Multilingual Denoising for RDF-to-Text Generation
Zdeněk Kasner, Ondrej Dusek
WEBNLG 2020
Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking
A. C. Curry, Ioannis V. Papaioannou, Alessandro Suglia, Shubham Agarwal, Igor Shalyminov, Xinnuo Xu, Ondrej Dusek, Arash Eshghi, Ioannis Konstas, Verena Rieser, Oliver Lemon
Alana: Social Dialogue using an Ensemble Model and a Ranker trained on User Feedback
Ioannis V. Papaioannou, A. C. Curry, Jose L. Part, Igor Shalyminov, Xu Xinnuo, Yanchao Yu, Ondrej Dusek, Verena Rieser, Oliver Lemon
A Context-aware Natural Language Generation Dataset for Dialogue Systems
Ondrej Dusek, Filip Jurcícek
Translation Model Interpolation for Domain Adaptation in TectoMT
Rudolf Rosa, Ondrej Dusek, M. Novák, M. Popel
Deep Machine Translation Workshop 2015
Semi-Automatic Detection of Multiword Expressions in the Slovak Dependency Treebank
Daniela Majchráková, Ondrej Dusek, Jan Haji, A. Kar, Ová, R. Garabík
CLIB 2014