Roger P. Levy
10 papers · 2006–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (27) π Academic Marathon Β· Ultra π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π±
Topic Pioneer
π§¬
Topic Evolution
π
Keyword Champion
π
Keyword Trendsetter Combo
(4)
π
Trend Setter
β
The Questioner
π
Conference Pioneer
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(61)
Venues
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(7)
Interdisciplinary
(5)
Natural Language Processing
(5)
Bayesian & Probabilistic Β· Artificial Intelligence
(4)
Linguistics
(4)
Understanding
(4)
Machine Learning
(3)
Cognitive Science
(3)
Optimization & Theory
(3)
Deep Learning
(1)
Mathematics & Optimization
(1)
Applications
(1)
Bayesian & Probabilistic Β· Machine Learning
(1)
Learning Types
(1)
Keywords
information theory
(2)
language model
(2)
sequential monte carlo
(2)
noisy channel model
(2)
emergent communication
(2)
logistic regression
(1)
cognitive modeling
(1)
reinforcement learning
(1)
language optimization
(1)
syntactic reduction
(1)
communicative efficiency
(1)
visual reasoning
(1)
bayesian inference
(1)
utility optimization
(1)
predictability estimation
(1)
probabilistic inference
(1)
information density
(1)
language production
(1)
structural cues
(1)
language understanding
(1)
Papers
Implicit Representations of Grammaticality in Language Models
ACL 2026
Readers make targeted regressions to plausible errors in reanalysis of βnoisy-channel garden-pathβ sentences
CoNLL 2026
On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts
EMNLP 2025
Resource-Rational Noisy-Channel Language Processing: Testing the Effect of Algorithmic Constraints on Inferences
EMNLP 2025
Bridging semantics and pragmatics in information-theoretic emergent communication
NeurIPS 2024
Image-conditioned human language comprehension and psychometric benchmarking of visual language models
CoNLL 2024
Trading off Utility, Informativeness, and Complexity in Emergent Communication
NeurIPS 2022
Grammar-Based Grounded Lexicon Learning
NeurIPS 2021
Modeling the effects of memory on human online sentence processing with particle filters
NeurIPS 2008
Speakers optimize information density through syntactic reduction
NeurIPS 2006