| 2026 | CoNLL | Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences. | Thomas Hikaru Clark, Roger P. Levy, Edward Gibson |
| 2025 | CogSci | A Model of Approximate and Incremental Noisy-Channel Language Processing. | Thomas Hikaru Clark, Jacob Hoover Vigly, Edward Gibson, Roger Levy |
| 2025 | EMNLP | Resource-Rational Noisy-Channel Language Processing: Testing the Effect of Algorithmic Constraints on Inferences. | Thomas Hikaru Clark, Jacob Hoover Vigly, Edward Gibson, Roger P. Levy |
| 2024 | CogSci | Inferring errors and intended meanings with a generative model of language production in aphasia. | Thomas Hikaru Clark, Edward Gibson, Roger Levy |
| 2023 | CogSci | Context-sensitive features predict sentence memorability in the absence of memorable words. | Thomas Hikaru Clark, Greta Tuckute, Bryan Medina, Evelina Fedorenko |
| 2022 | ACL | Analyzing Wrap-Up Effects through an Information-Theoretic Lens. | Clara Meister, Tiago Pimentel, Thomas Hikaru Clark, Ryan Cotterell, Roger Levy |
| 2022 | CogSci | Evidence for Availability Effects on Speaker Choice in the Russian Comparative Alternation. | Thomas Hikaru Clark, Ethan Gotlieb Wilcox, Edward Gibson, Roger Levy |
| 2021 | EMNLP | Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT. | Zaiqiao Meng, Fangyu Liu, Thomas Hikaru Clark, Ehsan Shareghi, Nigel Collier |