Presentations

Upcoming

December 11, Host, Responsible AI Roundtable
December 10, Generalisation in generative AI, Local workshop in Amsterdam
December 7, Generalisation in LLMs - and beyond, CliC-it
August 17, Generalisation in LLMs – and beyond, Repl4NLP
August 16, Evaluation data contamination:how much is there, and how much does it actually matter? CONDA
April 18, Large language models in the workplace, Erasmus Data Summit
January 24, Evaluation, generalisation and understanding in the era of LLMs, ILLC

April 13, The (un?)importance of generalisation in NLP. Generalisation in minds and machines
April 11, The (un?)importance of generalisation in NLP. MSR Montreal seminar series
*January 27, GenBench: State-of-the-art generalisation research in NLP. Cambridge NLP Seminar series
January 6, State-of-the-art generalisation research in NLP. ALiaS: Amsterdam Lectures in Artificial Intelligence and Society.

November 3, State-of-the-art generalisation research in NLP. Deep Learning & AI Talks @ Qualcomm
October 20, State-of-the-art generalisation research in NLP. Deep Mind reading group
June 29-30, The challence of compositionality for AI
June 15, Evaluating generalisation in natural language processing models, ODSC Europe
May 19, Are neural networks compositional, and how do we even measure that? Workshop on reasoning and neural models
April 14, Evaluating generalisation in neural networks for NLP, Stanford NLP Seminar

August 9, Compositionality in the era of neural networks. Keynote at the workshop Computational and experimental explanations in semantics and pragmatics.
[slides]
April 28, Compositionality Decomposed: how do neural networks generalise? Tel Aviv University (virtual talk).
March 17, Kunnen we kunstmatige intelligentie nog doorgronden? Studium Generale, Utrecht (virtual talk).
[recording]
February 11, Compositionality decomposed: how do neural networks generalise? Woman@CL, Cambridge (virtual talk).
February 5, Compositionality decomposed: how about natural language? Rijksuniversiteit Groningen, Groningen (virtual talk).

October 30, Neural networks as explanatory models of language processing, ILCC Seminar at the University of Edinburgh, Edinburgh (virtual talk)
[abstract]
September 17, Neural networks as explanatory models. AllenNLP, Seattle (virtual talk)

November 4, Syntax in neural language models: a case study, Universiteit Utrecht, Utrecht.
[slides]
October 9 Subject verb agreement in neural language models – how, when and where? Johns Hopkins University, Baltimore.
[slides]
October 1, What do they learn? Neural networks, compositionality and interpretability, Computational Cognition workshop, Osnabruek.
[slides] [recording]
September 3. Guest speaker and panelist at the public event When fake looks all too real: the technology behind Deep Fake, SPUI25, Amsterdam.
[slides] [recording]
June 18. The typology of emergent languages. Interaction and the Evolution of Linguistic Complexity, Edinburgh.
[slides]
May 6. The compositionality of neural networks: integrating symbolism and connectionism. CS&AI / SIKS workshop on analyzing and interpreting neural networks for NLP, ‘s-Hertogenbosch.
[slides]
April 18. The compositionality of neural networks: integrating symbolism and connectionism. Internal talk at Saarland University, Saarbrücken.
[slides]
March 14. On neural networks and compositionality. Internal seminar at École normale supérieure, Paris.
[slides]

July 18, 2018. Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure. IJCAI.
[slides]
June 12, 2018. Learning compositionally through attentive guidance. Internal seminar at the University of Copenhagen.
[slides]

May 9, 2017. Processing hierarchical structure with RNNs. Dagstuhl seminar on Human-like neural-symbolic computing.
[slides]
December 7, 2017. The grammar of neural networks. SMART workshop Grammars, Computation & Cognition, Amsterdam.
[slides]
December 15, 2017. Hierarchical compositionality in recurrent neural networks. Internal seminar at Rijksuniversiteit Groningen.
[slides]

May 25, 2016. POS-tagging of Historical Dutch. LREC, Portoroz.
November 22, 2016. How may neural networks process hierarchical structure? Insights from recursive and recurrent networks learning arithmetics. Logic Tea at the University of Amsterdam.
[slides]

June 8, 2015. Using Parallel Data to improve Part-of-Speech tagging of 17th century Dutch. DH Benelux, Antwerp.