Skip to main content
Flowers in Fellows Garden at Magdalene College Cambridge

Mr Rowan Hall Maudslay

Mr Rowan Hall Maudslay is a PhD student at the University of Cambridge, and a Bye-Fellow of Magdalene College.

Prior to that, he was a research assistant at ETH Zürich, and before that he completed his BA and MEng, both in Computer Science, at Cambridge. He is currently funded by the Leslie Wilson Vice-Chancellor's Scholarship, and his research is additionally supported by a Turing Institute Enrichment Award.

Rowan’s research concerns people's ability to perceive abstract similarities shared by disparate things, which manifests in analogy and metaphor. He is currently studying this ability through the lens of conventional metaphors, which are metaphors that are widely used by a language community, and can be found in dictionaries. Conventional metaphors provide a unique opportunity to analyse analogy and metaphor, which have both so far been elusive and difficult to study. Previously, his research has focused on the interpretability of neural networks, and gender-bias mitigation in machine-learnt models.

Selected Publications

For the most up-to-date version please refer to Google scholar.

R. H. Maudslay and S. Teufel. 2022. Homonymy Information for English WordNet. In Proceedings of the GLOBALEX Workshop on Linked Lexicography.

R. H. Maudslay and R. Cotterell. 2021. Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing. In Proceedings of the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).

T. Pimentel, R. H. Maudslay, D. Blasi, and R. Cotterell. 2020. Speakers Fill Lexical Semantic Gaps with Context. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).

R. H. Maudslay, T. Pimentel, R. Cotterell, and S. Teufel. 2020. Metaphor Detection Using Context and Concreteness. In Proceedings of the Second Workshop on Figurative Language Processing.

R. H. Maudslay, J. Valvoda, T. Pimentel, A. Williams and R. Cotterell. 2020. A Tale of a Probe and a Parser. In Proceedings of the 2020 Annual Conference of the Association for Computational Linguistics (ACL).

T. Pimentel, J. Valvoda, R. H. Maudslay, R. Zmigrod, A. Williams and R. Cotterell. 2020. Information-Theoretic Probing for Linguistic Structure. In Proceedings of the 2020 Annual Conference of the Association for Computational Linguistics (ACL).

R. H. Maudslay, H. Gonen, R. Cotterell and S. Teufel. 2019. It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP).