Kate McCurdy

I’m a postdoctoral researcher working with Michael Hahn. I recently completed my PhD in the School of Informatics, University of Edinburgh. I’ve also studied at McGill and Potsdam, worked as a researcher at Microsoft and Harvard, and founded a computational linguistics engineering team in the language-learning startup Babbel.

I’m a computational linguist with psycholinguistic training and broad interests in language and cognition. My research combines computational modeling and behavioral experiments to address fundamental scientific questions about how human language is structured and processed. I focus particularly on generalization and how it works in inflectional morphology.

I recently led a survey with Paul Smolensky and colleagues at Microsoft Research to see what researchers think about compositionality in neural network models. Data collection is complete, but you can still take the survey yourself and check our paper to see how your views fit with the field as a whole!

selected publications

Most German Speakers Ignore the Cue That Best Predicts Plural Class

Kate McCurdy, Timothy J. O’Donnell, Adam Lopez, and 1 more author

Open Mind, 2025

DOI Bib HTML

@article{mccurdy_most_2025,
  title = {Most {German} {Speakers} {Ignore} the {Cue} {That} {Best} {Predicts} {Plural} {Class}},
  author = {McCurdy, Kate and O'Donnell, Timothy J. and Lopez, Adam and Goldwater, Sharon},
  journal = {Open Mind},
  volume = {9},
  pages = {2175--2204},
  year = {2025},
  doi = {10.1162/opmi_a_320},
}

Lossy Context Surprisal Predicts Task-Dependent Patterns in Relative Clause Processing

Kate McCurdy, and Michael Hahn

In Proceedings of the 28th Conference on Computational Natural Language Learning, 2024

Abs Bib HTML Code

English relative clauses are a critical test case for theories of syntactic processing. Expectation- and memory-based accounts make opposing predictions, and behavioral experiments have found mixed results. We present a technical extension of Lossy Context Surprisal (LCS) and use it to model relative clause processing in three behavioral experiments. LCS predicts key results at distinct retention rates, showing that task-dependent memory demands can account for discrepant behavioral patterns in the literature.
@inproceedings{mccurdy_lossy_2024, address = {Miami, FL, USA}, title = {Lossy {Context} {Surprisal} {Predicts} {Task}-{Dependent} {Patterns} in {Relative} {Clause} {Processing}}, urldate = {2024-11-20}, booktitle = {Proceedings of the 28th {Conference} on {Computational} {Natural} {Language} {Learning}}, publisher = {Association for Computational Linguistics}, author = {McCurdy, Kate and Hahn, Michael}, editor = {Barak, Libby and Alikhani, Malihe}, year = {2024}, pages = {36--45}, file = {Full Text PDF:C\:\\Users\\Kate\\Zotero\\storage\\3NYFTL2B\\McCurdy and Hahn - 2024 - Lossy Context Surprisal Predicts Task-Dependent Pa.pdf:application/pdf} }
Toward Compositional Behavior in Neural Models: A Survey of Current Views

Kate McCurdy, Paul Soulos, Paul Smolensky, and 2 more authors

In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Abs Bib HTML

Compositionality is a core property of natural language, and compositional behavior (CB) is a crucial goal for modern NLP systems. The research literature, however, includes conflicting perspectives on how CB should be defined, evaluated, and achieved. We propose a conceptual framework to address these questions and survey researchers active in this area.We find consensus on several key points. Researchers broadly accept our proposed definition of CB, agree that it is not solved by current models, and doubt that scale alone will achieve the target behavior. In other areas, we find the field is split on how to move forward, identifying diverse opportunities for future research.
@inproceedings{mccurdy_toward_2024, address = {Miami, Florida, USA}, title = {Toward {Compositional} {Behavior} in {Neural} {Models}: {A} {Survey} of {Current} {Views}}, shorttitle = {Toward {Compositional} {Behavior} in {Neural} {Models}}, urldate = {2024-11-20}, booktitle = {Proceedings of the 2024 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}}, publisher = {Association for Computational Linguistics}, author = {McCurdy, Kate and Soulos, Paul and Smolensky, Paul and Fernandez, Roland and Gao, Jianfeng}, editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung}, year = {2024}, pages = {9323--9339}, file = {Full Text PDF:C\:\\Users\\Kate\\Zotero\\storage\\4PQEFYE4\\McCurdy et al. - 2024 - Toward Compositional Behavior in Neural Models A .pdf:application/pdf}, }