--- title: "Roger Levy — papers and cards" description: "Roger Levy: 2 paper cards in the Research library (2020–2023), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/roger-levy/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/roger-levy/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Roger Levy # Roger Levy 2 paper cards in the Research library · 2020–2023 Roger Levy wrote 2 of the papers Mova reads, in 2020–2023; often with [Jennifer Hu](https://md.research.elamur.ai/free/en/authors/jennifer-hu/), Jonathan Malmaud, [Judith Degen](https://md.research.elamur.ai/free/en/authors/judith-degen/). [OpenAlex](https://openalex.org/A5090215557) · [ORCID](https://orcid.org/0000-0002-4493-8864) · [**h-index 55**](https://openalex.org/authors/A5090215557) · [23036 citations](https://openalex.org/authors/A5090215557) · [343 works](https://openalex.org/works?filter=author.id:A5090215557) — openalex-snapshot, 2026-10-14 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Roger+Levy) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Roger+Levy) · [dblp](https://dblp.org/search?q=Roger+Levy) · [ACL Anthology](https://aclanthology.org/search/?q=Roger+Levy) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Roger+Levy) ## Ideas Mova took (1) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **kept** — Critical-span ablation as a validity check of course questions: remove the critical sentence; the student should fall to guessing on that question. Questions still answered right are guessable from elsewhere or from the options and should be fixed or marked. *([STARC: Structured Annotations for Reading Comprehension](https://md.research.elamur.ai/free/en/papers/berzak-2020-starc-structured-annotations-reading-comprehension/) · critical-span ablation per lesson as the «key sentences removed» control (dba7f8c6e))* ## Papers 1. **[Expectations over Unspoken Alternatives Predict Pragmatic Inferences](https://md.research.elamur.ai/free/en/papers/hu-2023-expectations-over-unspoken-alternatives-predict/)** *(2023)* Scalar inferences ("some" implies "not all") vary a lot from one instance to another, and across scales such as "good, excellent". 2. **[STARC: Structured Annotations for Reading Comprehension](https://md.research.elamur.ai/free/en/papers/berzak-2020-starc-structured-annotations-reading-comprehension/)** *(2020)* `1 idea kept` STARC is a scheme for four-option reading questions in which the options have fixed roles tied to marked text spans: A is right and rests on a «critical span»; B mentions the critical span but misunderstands it; C refers to a separate «distractor span»; D has no support in the text. ## Co-authors (5) - [Jennifer Hu](https://md.research.elamur.ai/free/en/authors/jennifer-hu/) - Jonathan Malmaud - [Judith Degen](https://md.research.elamur.ai/free/en/authors/judith-degen/) - [Sebastian Schuster](https://md.research.elamur.ai/free/en/authors/sebastian-schuster/) - [Yevgeni Berzak](https://md.research.elamur.ai/free/en/authors/yevgeni-berzak/) ## More papers in the library (6) Pages of the Research library: our summary, the ideas, references and who cites each. - [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://md.research.elamur.ai/free/en/papers/olausson-2023-linc-neurosymbolic-approach-logical-reasoning/) — Theo X. Olausson, Alex Gu, Benjamin Lipkin, et al. · 2023 - [Prompting is not a substitute for probability measurements in large language models](https://md.research.elamur.ai/free/en/papers/hu-2023-prompting-is-not-substitute-probability/) — Jennifer Hu, Roger Levy · 2023 - [A closer look at the performance of neural language models on reflexive anaphor licensing](https://md.research.elamur.ai/free/en/papers/hu-2020-closer-look-performance-neural-language/) — Jennifer Hu, Sherry Yong Chen, Roger Levy · 2020 - [SyntaxGym: An Online Platform for Targeted Evaluation of Language Models](https://md.research.elamur.ai/free/en/papers/gauthier-2020-syntaxgym-online-platform-targeted-evaluation/) — Jon Gauthier, Jennifer Hu, Ethan Wilcox, et al. · 2020 - [Neural language models as psycholinguistic subjects: Representations of syntactic state](https://md.research.elamur.ai/free/en/papers/futrell-2019-neural-language-models-as-psycholinguistic/) — Richard Futrell, Ethan Wilcox, Takashi Morita, et al. · 2019 - [What do RNN Language Models Learn about Filler-Gap Dependencies?](https://md.research.elamur.ai/free/en/papers/wilcox-2018-rnn-language-models-learn-about/) — Ethan Wilcox, Roger Levy, Takashi Morita, et al. · 2018