Josef Valvoda

University of Cambridge

I am a final-year PhD student at the University of Cambridge supervised by Professor Simone Teufel (Cambridge) and Professor Ryan Cotterell (ETH). Before joining the Natural Language and Information Processing group I’ve completed the MPhil in Advanced Computer Science also at the University of Cambridge. Before that, I’ve obtained a Bachelor of Law at the University of Exeter. I’m a member of Rycolab at ETH Zurich and fully funded by the Huawei Reseach Scholarship.

My PhD work focuses on Aritifical Intelligence and Law. I belive that automation is the key for widening access to justice. I think about what deep learning models can learn, have learned and should learn. I’m on the program committee of the Competition on Legal Information Extraction/Entailment (COLIEE), Natural Legal Language Processing Workshop (NLLP) and the International Workshop on Juris-informatics (JURISIN).

While Legal NLP is the focus of my thesis, I am also very much interested in broader NLP research. I have recently published work on testing the compositional behaviour of neural networks. Finally, I continue to collaborate on developing (probing) methods that could better our understanding of what the neural models learn.

Outside of my work in Cambridge, I’ve been frequenting Japan’s National Institute of Informatics (NII), worked with startups (TechWolf) and interned as AI/ML researcher at Apple and Applied Scientist at Amazon.

You can find me on: Twitter, GitHub, LinkedIn or the department website. PDF copy of my CV is here.

selected publications

  1. TACL
    On the Role of Negative Precedent in Legal Outcome Prediction
    Valvoda, Josef, Cotterell, Ryan, and Teufel, Simone
    Transactions of the Association for Computational Linguistics 2023
    PDF
  2. COLING
    Benchmarking Compositionality with Formal Languages
    Valvoda, Josef, Saphra, Naomi, Rawski, Jonathan, Williams, Adina, and Cotterell, Ryan
    In Proceedings of the 29th International Conference on Computational Linguistics 2022
    PDF
  3. NAACL
    What About the Precedent: An Information-Theoretic Analysis of Common Law
    Valvoda, Josef, Pimentel, Tiago, Stoehr, Niklas, Cotterell, Ryan, and Teufel, Simone
    In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2021
    PDF
  4. ACL
    Information-Theoretic Probing for Linguistic Structure
    Pimentel, Tiago, Valvoda, Josef, Maudslay, Rowan Hall, Zmigrod, Ran, Williams, Adina, and Cotterell, Ryan
    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020 2020
    PDF