Ondřej Dušek

office
N233
office hours
email me to arrange a meeting
email
odusek@ufal.mff.cuni.cz
address
IMPAKT – „N“
V Holešovičkách 747/2
180 00 Praha 8
Czech Republic

Main Research Interests

  • Natural language generation
  • Spoken dialogue systems and chatbots
  • Evaluation methods for NLG/dialogue/NLP

Projects

Current

  • NG-NLG – Language generation with neural & symbolic methods (ERC StG, 2022-2027)
  • EDU-AI – Education chatbot assistant (Czech Technical Agency, 2021-2023)

Past

  • THEaiTRE – Automatically generating a theatre play (Czech Technical Agency, 2020-2022)
  • NaMuDDiS – Natural Multi-domain Dialogue Systems (Charles University funded, 2019-2021)
  • METOD – dialogue management (industry cooperation with Agnostix co-funded by City of Prague, 2020)

At Heriot-Watt University in Edinburgh (2016-2018):

During my Ph.D. study (2011-2016):

  • AdaNLG – adaptive natural language generator (2014-2016)
  • Vystadial – statistical spoken dialogue system (2013-2016)
  • QTLeap – semantic machine translation (2013-2016)
  • Khresmoi – medical information retrieval (working on machine translation, 2013-2014)
  • FAUST – improving machine translation fluency (2011-2013)

Teaching

List of classes

Selected Bibliography

Students

Students I supervise:

  • Zdeněk Kasner (Ph.D. since 2019)
  • Sourabrata Mukherjee (Ph.D. since 2019)
  • Ondřej Plátek (Ph.D. since 2021)
  • Patrícia Schmidtová (completed BSc. with Vojtěch Hudeček, 2018–2019; completed MSc. 2020–2022, PhD. since 2023)
  • František Trebuňa (MSc. since 2021)
  • Nalin Kumar (MSc. since 2022)
  • Borek Požár (completed BSc. with Martin Čmejrek & Jan Cuřín, 2020-2021, MSc. since 2023)
  • Darya Hryhoryeva (MSc. since 2024)
  • Karen Li (MSc. with Simone Balloccu & Vera Demberg (LCT Saarland Uni) since 2023)
  • Ivan Kartáč (MSc. with Mateusz Lango since 2023)
  • Damian Waloszek (MSc. since 2023)
  • Kristýna Klesnilová (MSc. with Mateusz Lango since 2023)
  • Michelle Elizabeth (MSc. with Lina Rojas-Barajona (LCT, Orange Labs) since 2024)
  • Ulvi Mamadov (MSc. since 2024)
  • Rafael Sargsyan (BSc. with Simone Balloccu since 2023)

My former students:

  • Shubham Agarwal (Ph.D. at Heriot-Watt, with Verena Rieser & Ioannis Konstas, 2017-2019)
  • Ekaterina Garanina (completed MSc., LCT with Uni Groningen, with Gertjan van Noord, 2022-2024)
  • Peter Grajcar (completed MSc. 2022-2023)
  • Vojtěch Hudeček (completed Ph.D., 2019-2024 (previously supervised by Zdeněk Žabokrtský))
  • Vojtěch John (completed BSc. 2021-2022)
  • Jonáš Kulhánek (completed MSc. 2020-2021)
  • Ondřej Motlíček (completed MSc. 2021–2022)
  • Tomáš Nekvinda (completed MSc. 2019–2020; Ph.D. 2020-2022)
  • Saad Obaid ul Islam (completed MSc., LCT with Uni Saarbrücken, with Vera Demberg & Iza Škrjanec, 2022-2023)
  • Jakub Růžička (completed BSc. with Jan Cuřín & Martin Čmejrek, 2022-2023)
  • Kristína Szabová (completed MSc. 2022-2023)
  • Jaroslav Šafář (completed MSc. 2021-2023)
  • Daniel Štancl (Ph.D. 2020-2022)
  • Jan Vainer (completed MSc. 2019–2020)
  • Xinnuo Xu (completed Ph.D., CDT Robotics Edinburgh, with Verena Rieser & Ioannis Konstas, 2016–2021)

News

2023/02/21: Our paper titled Barriers and enabling factors for error analysis in NLG research (van Miltenburg et al.) was accepted at the North European Journal of Language Technology. The journal is open-access.

2023/02/09: I gave a talk on Robust Data-to-text Generation with Pretrained Language Models at the Prague Computer Science seminar.

2023/01/20: Our paper Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models (Kasner et al.) was accepted at EACL. A preprint is on arXiv.

2022/09/22: Our paper titled Learning Interpretable Latent Dialogue Actions With Less Supervision (Hudeček & Dušek) was accepted at AACL-IJCNLP. A preprint is on arXiv.

2022/07/15: Our paper titled AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog (Nekvinda & Dušek) was accepted at SIGDIAL. It is now available on arXiv.

2022/06/30: I gave a talk on Neural Conversational AI at the MLSS^N summer school in Cracow. You can get the slides here, live recording on Youtube is here.

2022/06/01: The ERC NG-NLG project officially started in April. I was hiring a post-doc – see details here.

2022/04/06: Our paper DIASER: A Unifying View on Task-Oriented Dialogue Annotation (Hudeček et al.) was accepted for LREC 2022. You can now see the paper in the proceedings.

2022/03/22: I gave a talk at the AICZECHIA seminar on Large Language Models for Data-to-text Generation. You can get the slides here, recording will be on YouTube soon.

2022/02/28: Our paper titled Neural Pipeline for Data-to-text Generation (Kasner & Dušek) was accepted at the ACL conference. You can see it now in ACL Anthology.

2022/02/14: We're starting another run of the Dialogue Systems course, this time it's included in the prg.ai minor as well.

2022/01/10: I was awarded an ERC grant titled Next-Generation Natural Language Generation. It joins explicit semantics and neural language models in order to get natural and accurate NLG outputs. You can read a short report in the UK Forum magazine, more info will follow.

Biographical

Tools I'm participating on

  • Alex – spoken dialogue system framework
  • Flect – statistical morphology generation
  • MTMonkey – machine translation web services infrastructure
  • RatPred – trainable NLG quality estimation
  • TGen – a statistical natural language generator
  • Treex – a modular NLP toolkit

Personal webpage