Publications

Find me on Google Scholar here.

Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?
Joris Baan, Maartje ter Hoeve, Marlies van der Wees, Anne Schuth, Maarten de Rijke. In Proceedings of the SIGIR Workshop FACTS-IR 2019

On the Realization of Compositionality in Neural Networks
Joris Baan, Jana Leible, Mitja Nikolaus, David Rau, Dennis Ulmer, Tim Baumgartner, Dieuwke Hupkes, Elia Bruni. In proceedings of the ACL Workshop BlackboxNLP 2019