Ondřej Dušek
Main Research Interests
- Natural language generation
- Spoken dialogue systems and chatbots
- Evaluation methods for NLG/dialogue/NLP
Projects
Current
- NaMuDDiS – Natural Multi-domain Dialogue Systems (Charles University funded, 2019-2021)
- THEaiTRE – Automatically generating a theatre play (Czech Technical Agency, 2020-2022)
- EDU-AI – Education chatbot assistant (Czech Technical Agency, 2021-2023)
Past
- METOD – dialogue management (industry cooperation with Agnostix co-funded by City of Prague, 2020)
At Heriot-Watt University in Edinburgh (2016-2018):
- DILiGENt – natural language generation
- MaDrIgAL – spoken dialogue systems
- Alexa Prize Challenge – chatbots (Alana – 2x finalist team, 2x 3rd place)
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 classesNPFL099 Statistical dialogue systemsNPFL123 Dialogue systems
Students
Students I supervise:
- Vojtěch Hudeček (Ph.D. at Charles Uni, with Zdeněk Žabokrtský, since 2018)
- Zdeněk Kasner (Ph.D. at Charles Uni since 2019)
- Sourabrata Mukherjee (Ph.D. at Charles Uni since 2019)
- Tomáš Nekvinda (completed MSc. at Charles Uni, 2019–2020; Ph.D. since 2020)
- Daniel Štancl (Ph.D. at Charles Uni since 2020)
- Ondřej Plátek (Ph.D. at Charles Uni since 2021)
- Patrícia Schmidtová (completed BSc. at Charles Uni, with Vojtěch Hudeček, 2018–2019; MSc. since 2020)
- Jaroslav Šafář (MSc. at Charles Uni since 2021)
- Ondřej Motlíček (MSc. at Charles Uni since 2021)
- František Trebuňa (MSc. at Charles Uni since 2021)
- Hana Roubalová (BSc. at Charles Uni since 2021)
- Vojtěch John (BSc. at Charles Uni since 2021)
My former students:
- Shubham Agarwal (Ph.D. at Heriot-Watt, with Verena Rieser & Ioannis Konstas, 2017-2019)
- Jonáš Kulhánek (completed MSc. at Charles Uni, 2020-2021)
- Ondřej Měkota (MSc. at Charles Uni, 2020)
- Borek Požár (completed BSc. at Charles Uni, with Martin Čmejrek & Jan Cuřín, 2020-2021)
- Jan Vainer (completed MSc. at Charles Uni, 2019–2020)
- Xinnuo Xu (completed Ph.D., CDT Robotics Edinburgh, with Verena Rieser & Ioannis Konstas, 2016–2021)
News
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. Preprint is coming soon.
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.
2021/10/08 I co-organized the 6th workshop on Search-oriented Conversational AI. You can have a look at the report in the SIGIR Forum.
2021/09/22: Our paper titled AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models (Kulhánek et al.) was accepted at the NLP4ConvAI workshop at EMNLP.
2021/09/21: Our INLG paper on NLG error analysis (van Miltenburg et al.) was awarded a Commendation for an outstanding position paper!
2021/08/26: Our paper MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization (Xu et al., with HWU) was accepted to EMNLP Findings.
2021/08/06: I was involved in the GEM benchmark – Generation, Evaluation & Metrics. This was presented at an ACL workshop and included a shared task. You can have a look at the workshop website.
2021/07/26: I have 2 papers accepted at INLG 2021 – Underreporting of errors in NLG output, and what to do about it (van Miltenburg et al., multi-party collaboration) and the winning automatic metric for the Accuracy Evaluation Shared Task, titled Text-in-Context: Token-Level Error Detection for Table-to-Text Generation (Kasner et al.) with Simon Mille from Pompeu Fabra University.
2021/06/15: I started my summer research visit at Prof. Milica Gašić's lab at Heinrich-Heine University Düsseldorf
2021/05/28: Our paper Shades of BLEU, Flavours of Success: The Case of MultiWOZ (Nekvinda & Dušek) was accepted to the GEM ACL Workshop.
2021/05/06: 2 papers accepted at ACL 2021 – AggGen: Ordering and Aggregating while Generating (Xu et al.) with Heriot-Watt University and Discovering Dialogue Slots with Weak Supervision (Hudeček et al.) with Zhou Yu from Columbia University.
2021/04/21: Our collaboration with LIMSI – Defining And Detecting Inconsistent System Behavior in Task-oriented Dialogues (Schaub et al.) was accepted to the TALN-RÉCITAL conference.
2021/04/26: The EDU-AI project (education chatbot) funded by the Czech Technical Agency has started.
Biographical
- My CV
- List of publications (incl. talks)
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