Paweł Budzianowski bio photo

Paweł Budzianowski

Machine Learning, Dialogue Systems, Artificial Intelligence

Email Scholar LinkedIn GitHub



  1. Hello, It’s GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems, The 3rd Workshop on Neural Generation and Translation, EMNLP, 2019.

    Paweł Budzianowski, Ivan Vulić

  2. Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling, EMNLP, 2019.

    Bo-Hsiang Tseng, Marek Rei, Paweł Budzianowski, Richard Turner, Bill Byrne, Anna Korhonen

  3. MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling, EMNLP 2018. [data] [code]

    Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Inigo Casanueva, Stefan Ultes, Osman Ramadan, Milica Gašić
    Best Resource Paper Award, 1 of 4 out of 548 accepted papers

  4. Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing, ACL 2018. [code]

    Osman Ramadan, Paweł Budzianowski, Milica Gašić

  5. Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation, ICASSP 2018.

    Christopher Tegho*, Paweł Budzianowski*, Milica Gašić
    Best Student Paper Award, 1 of 10 out of 1442 accepted papers

  6. Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces, IEEE Transaction on Audio, Speech and Language Processing, 2018.

    Gellert Weisz, Paweł Budzianowski, Pei-Hao Su, Milica Gašić

  7. Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation, Bayesian Deep Learning Workshop, NIPS 2017.

    Christopher Tegho*, Paweł Budzianowski*, Milica Gašić

  8. “A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management”, Deep Reinforcement Learning Symposium, NIPS 2017.

    Inigo Casanueva*, Paweł Budzianowski*, Pei-Hao Su*, Nikola Mrkšić, Tsung-Hsien Wen, Stefan Ultes, Lina Rojas-Barahona, Steve Young and Milica Gašić

  9. “Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning”, SIGDIAL 2017.

    Paweł Budzianowski, Stefan Ultes, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Iñigo Casanueva, Lina M. Rojas Barahona and Milica Gašić

  10. “Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management”, SIGDIAL 2017.

    Pei-Hao Su, Paweł Budzianowski, Stefan Ultes, Milica Gašić and Steve Young

  11. “Copula Models in Macroeconomic Analysis of Dependence”, (in Polish), Local, Regional and Global Economy, 2014.

    Paweł Budzianowski

*equal contribution

Collaborated Papers

  1. “Training Neural Response Selection for Task-Oriented Dialogue Systems”, ACL 2019

    Matthew Henderson, Ivan Vulić, Daniela Gerz, Iñigo Casanueva, Paweł Budzianowski, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrkšić, Pei-Hao Su

  2. “A Repository of Conversational Datasets”, NLP for ConvAI Workshop, ACL 2019

    Matthew Henderson, Paweł Budzianowski, Iñigo Casanueva, Sam Coope, Daniela Gerz, Girish Kumar, Nikola Mrkšić, Georgios Spithourakis, Pei-Hao Su, Ivan Vulić, Tsung-Hsien Wen

  3. “PyDial: A Multi-domain Statistical Dialogue System Toolkit”, ACL 2017

    Stefan Ultes, Lina M. Rojas Barahona, Pei-Hao Su, David Vandyke, Dongho Kim, Iñigo Casanueva, Paweł Budzianowski, Nikola Mrkšić, Tsung-Hsien Wen, Milica Gasic and Steve Young

Website articles

  1. Artificial Intelligence is Coming, Poznan Mathematical Foundation 2016
  2. Kepler’s laws, co-author, Poznan Mathematical Foundation, 2014


  1. Training Restricted Boltzmann Machines Using High-Temperature Expansion, Master’s Thesis, Engineering Department, University of Cambridge, first-class honours.
  2. Applications of copulas in calculating Value-at-Risk (in Polish), Master’s Thesis, Faculty of Mathematics and Computer Science, Adam Mickiewicz University in Poznan, first-class honours.