Wietse de Vries

Hi! I am a postdoctoral researcher in the Computational Linguistics group of the University of Groningen (The Netherlands). My current work is on low-resource speech technology 🗣️.

I am also a hobby beekeeper 🐝. Any beekeeping stuff can be found on hunneg.nl.

Profiles

Academic bio

• 2024
  -
  now
  Postdoctoral researcher in Speech Technology, University of Groningen.
• 2020
  -
  2024
  PhD in Computational Linguistics, University of Groningen PhD thesis: Evaluation and Adaptation of Neural Language Models for Under-Resourced Languages.
• 2018
  -
  2020
  Ma in Information Science, University of Groningen, cum laude.
• 2015
  -
  2018
  BSc in Information Science, University of Groningen, cum laude.

Publications

• Reihaneh Amooie, Wietse de Vries, Yun Hao and Jelske Dijkstra and Matt Coler and Martijn Wieling (2025)
  Enhancing Standard and Dialectal Frisian ASR: Multilingual Fine-tuning and Language Identification for Improved Low-resource Performance ICASSP 2025
  PDF
• Yun Hao, Reihaneh Amooie, Wietse de Vries, Thomas Tienkamp, Rik van Noord, Martijn Wieling (2024)
  Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion Interspeech 2024
  PDF Github Google Scholar
• Hedwig Sekeres, Wilbert Heeringa, Wietse de Vries, Oscar Yde Zwagers, Martijn Wieling, Goffe Jensma (2024)
  Developing Infrastructure for Low-Resource Language Corpus Building SIGUL 2024
  PDF Google Scholar ACL Anthology
• Clara Egger, Tommaso Caselli, Georgios Tziafas, Eugénie de Saint Phalle, Wietse de Vries (2024)
  Extracting and classifying exceptional COVID-19 measures from multilingual legal texts: The merits and limitations of automated approaches Regulation & Governance 18
  PDF Google Scholar
• Wietse de Vries, Martijn Wieling, Malvina Nissim (2023)
  DUMB: A Benchmark for Smart Evaluation of Dutch Models EMNLP 2023
  PDF Github Google Scholar ACL Anthology
• Wietse de Vries, Martijn Wieling, Malvina Nissim (2022)
  Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages ACL 2022
  PDF Github Google Scholar ACL Anthology
• Martijn Bartelds, Wietse de Vries, Faraz Sanal, Caitlin Richter, Mark Liberman, Martijn Wieling (2022)
  Neural Representations for Modeling Variation in Speech Journal of Phonetics 92
  PDF Github Google Scholar
• Wietse de Vries*, Martijn Bartelds*, Malvina Nissim, Martijn Wieling *equal contribution (2021)
  Adapting Monolingual Models: Data can be Scarce when Language Similarity is High Findings of ACL 2021
  PDF Github Google Scholar ACL Anthology
• Wietse de Vries, Malvina Nissim (2021)
  As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages Findings of ACL 2021
  PDF Github Google Scholar ACL Anthology
• Georgios Tziafas, Eugenie de Saint-Phalle, Wietse de Vries, Clara Egger, Tommaso Caselli (2021)
  A Multilingual Approach to Identify and Classify Exceptional Measures against COVID-19 Natural Legal Language Processing Workshop 2021
  PDF Google Scholar ACL Anthology
• Wietse de Vries, Andreas van Cranenburgh, Malvina Nissim (2020)
  What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models Findings of EMNLP 2020
  PDF Github Google Scholar ACL Anthology
• Wietse de Vries, Andreas van Cranenburgh, Arianna Bisazza, Tommaso Caselli, Gertjan van Noord, Malvina Nissim (2019)
  BERTje: A Dutch BERT model
  PDF Github Google Scholar
• Wietse de Vries (2019)
  Cognitively Plausible Computational Models of Lexical Processing Can Explain Variance in Human Word Predictions and Reading Times Artificial Intelligence and Machine Learning (BNAIC 2019)
  PDF Google Scholar