Grzegorz Chrupała
I am an Associate Professor at the department of Cognitive Science and Artificial Intelligence at Tilburg University.
I received my PhD from
the School of Computing at
Dublin City University. After that I worked as a researcher at the
Spoken Language Systems group
at Saarland University. I am
interested in computation in biological and artificial systems, and
connections between them.
See full bio.
Research in my lab focuses on computational approaches to multimodal communication. We often take inspiration from the ease which young children show for picking up languages they are exposed to with little effort and no explicit instruction. The information they rely on is messy and unstructured, but it is rich and multimodal, including speech and gestures, visual and auditory stimuli, and interaction with other people. In contrast, the typical way computers learn language is by reading billions of words of written text.
We work on enabling machines to access rich data in multiple modalities and find systematic connections between them as a way to learn language in a more natural and data-efficient manner.
We explore the limits of human-like learning, aiming to teach computers to deal not only with the world's largest languages, but also with those with little written material, or no writing system at all.
We also develop, apply, and evaluate techniques for understanding computations in deep learning architectures.
News
- I am publicity co-chair for Interspeech 2025.
- I am an action editor for TACL.
- Paper accepted to NAACL 2024: Encoding of lexical tone in self-supervised models of spoken language.
- I'm talking about putting natural back into Natural Language Processing at the 2nd Dutch Speech Tech Day.
- My course on Neural models of spoken language at the LOT Winter School 2024.
- Paper accepted to ICLR 2024: Quantifying the Plausibility of Context Reliance in Neural Machine Translation.
People
- Gaofei Shen. PhD candidate, Interpretability techniques for spoken language models.
- Gabriele Sarti. PhD candidate, User-centric interpretability for neural machine translation.
- Hosein Mohebbi. PhD candidate, Analyzing and interpreting deep neural models of language.
- Lisa Lepp. PhD candidate, Machine Translation for sign and spoken languages.
- Céline Angonin. PhD candidate, bioacoustics.
Alumni
- Chris Emmery. PhD thesis: User-Centered Security in Natural Language Processing.
- Bertrand Higy. Postdoc, Understanding visually grounded spoken language via multi-tasking.
- Patrick Bos. E-science engineer, Understanding visually grounded spoken language via multi-tasking.
- Christiaan Meijer. E-science engineer, Understanding visually grounded spoken language via multi-tasking.
- Ákos Kádár. PhD thesis: Learning Visually Grounded and Multilingual Representations.
Publications
For the complete list of publications check: Google Scholar | Semantic Scholar | DBLP | ACL Anthology | ORCID
Selected papers
- Nikolaus, M., Alishahi, A. & Chrupała, G. (2022). Learning English with Peppa Pig. Transactions of the Association for Computational Linguistics, 10, 922–936.
Paper | Code - Chrupała, G. (2022). Visually grounded models of spoken
language: A survey of datasets, architectures and evaluation
techniques. Journal of Artificial Intelligence Research, 73,
673-707.
Paper - Chrupała, G., & Alishahi, A. (2019). Correlating Neural
and Symbolic Representations of Language. In Proceedings of the 57th
Annual Meeting of the Association for Computational Linguistics
(pp. 2952-2962).
Paper | Code - Chrupała, G., Gelderloos, L., & Alishahi, A. (2017).
Representations of language in a model of visually grounded
speech signal. In Proceedings of the 55th Annual Meeting of the
Association for Computational Linguistics (Volume 1: Long Papers)
(pp. 613-622).
Paper | Code - Kádár, A., Chrupała, G., & Alishahi, A. (2017). Representation
of linguistic form and function in recurrent neural
networks. Computational Linguistics, 43(4):761-780.
Paper | Code
Recent Talks
- Putting Natural in NLP. University of Groningen.
- Learning language from Peppa Pig. ILLC seminar, University of Amsterdam.
- Visually Grounded Models of Spoken Language and their Analysis. Lecture at ALPS Winter School. Video
- Investigating neural representations of speech and language. Keynote at the Nordic Conference on Computational Linguistics (NoDaLiDa), October 2019.
Supervision
Selected MSc theses
- Jean Constantin. 2022. Identification of causal discourse relations in French text using machine-translated training resources. Tilburg University.
- Kristel van Rooij. 2021. Gender classification of first names using Long Short-Term Memory recurrent neural networks and support vector machine in various countries. Tilburg University.
- Aayushi Pandey. 2020. Emotion recognition in a model of visually grounded speech. Tilburg University.
- Dmitrijs Surenans. 2020. Machine Learning Explainability In Finance: An Application to Default Risk Analysis. Tilburg University.
Bio
Grzegorz Chrupała is an Associate Professor at the Department of Cognitive Science and Artificial Intelligence at Tilburg University. Previously he did postdoctoral research at the Spoken Language Systems group at Saarland University. He received his doctoral degree from the School of Computing at Dublin City University.
He is interested in computation in biological and artificial systems, and connections between them. His research focuses especially on computational models of learning (spoken) language in naturalistic multimodal settings, as well as analysis and interpretation of representations emerging in deep learning architectures.
He is an Action Editor for TACL, and regularly serves as Senior Area Chair for major NLP and AI conferences such as ACL and EMNLP. He was one of the creators of the popular BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. His research has been funded by the Dutch Research Council (NWO).
Contact
Department of Cognitive Science and Artificial Intelligence
Tilburg University
PO Box 90153
5000 LE Tilburg
The Netherlands
Bluesky: @grzegorz.chrupala.me
Twitter: @gchrupala
Web: grzegorz.chrupala.me
Email: grzegorz@chrupala.me