Ryan Cotterell

Prefix Parsing is Just Parsing ACL 2026 Probing for Reading Times ACL 2026 On the Proper Treatment of Units in Surprisal Theory ACL 2026 Characterizing the Expressivity of Local Attention in Transformers ACL 2026 Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo ICLR 2025 Taxonomy-Aware Evaluation of Vision-Language Models CVPR 2025 Controllable Context Sensitivity and the Knob Behind It ICLR 2025 Training Neural Networks as Recognizers of Formal Languages ICLR 2025 The Foundations of Tokenization: Statistical and Computational Concerns ICLR 2025 Gumbel Counterfactual Generation From Language Models ICLR 2025 Variational Best-of-N Alignment ICLR 2025 Syntactic Control of Language Models by Posterior Inference ACL 2025 Unique Hard Attention: A Tale of Two Sides ACL 2025 The Harmonic Structure of Information Contours ACL 2025 Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation NAACL 2025 How Persuasive Is Your Context? EMNLP 2025 A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior ACL 2025 Information Locality as an Inductive Bias for Neural Language Models ACL 2025 A Distributional Perspective on Word Learning in Neural Language Models NAACL 2025 A Practical Method for Generating String Counterfactuals NAACL 2025 From Language Models over Tokens to Language Models over Characters ICML 2025 Language Models over Canonical Byte-Pair Encodings ICML 2025 Findings of the Third BabyLM Challenge: Accelerating Language Modeling Research with Cognitively Plausible Data EMNLP 2025 The Role of n-gram Smoothing in the Age of Neural Networks NAACL 2024 Transformers Can Represent n-gram Language Models NAACL 2024 Lower Bounds on the Expressivity of Recurrent Neural Language Models NAACL 2024 Representation Surgery: Theory and Practice of Affine Steering ICML 2024 Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? ICML 2024 On Affine Homotopy between Language Encoders NIPS 2024 What Do Language Models Learn in Context? The Structured Task Hypothesis. ACL 2024 On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning ACL 2024 Context versus Prior Knowledge in Language Models ACL 2024 What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages ACL 2024 Computational Expressivity of Neural Language Models ACL 2024 On Efficiently Representing Regular Languages as RNNs ACL 2024 Direct Preference Optimization with an Offset ACL 2024 When is a Language Process a Language Model? ACL 2024 Principled Gradient-Based MCMC for Conditional Sampling of Text ICML 2024 Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora CONLL 2024 Generalized Measures of Anticipation and Responsivity in Online Language Processing EMNLP 2024 Activation Scaling for Steering and Interpreting Language Models EMNLP 2024 A Transformer with Stack Attention NAACL 2024 Towards Explainability in Legal Outcome Prediction Models NAACL 2024 Efficiently Computing Susceptibility to Context in Language Models EMNLP 2024 Surprise! Uniform Information Density Isn’t the Whole Story: Predicting Surprisal Contours in Long-form Discourse EMNLP 2024 On the Proper Treatment of Tokenization in Psycholinguistics EMNLP 2024 A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors EMNLP 2024 Can Transformers Learn n-gram Language Models? EMNLP 2024 Reverse-Engineering the Reader EMNLP 2024 An L* Algorithm for Deterministic Weighted Regular Languages EMNLP 2024 On the Role of Context in Reading Time Prediction EMNLP 2024 Language Model Quality Correlates with Psychometric Predictive Power in Multiple Languages EMNLP 2023 Generalizing Backpropagation for Gradient-Based Interpretability ACL 2023 A Fast Algorithm for Computing Prefix Probabilities ACL 2023 Hexatagging: Projective Dependency Parsing as Tagging ACL 2023 Generating Text from Language Models ACL 2023 A Formal Perspective on Byte-Pair Encoding ACL 2023 Revisiting the Optimality of Word Lengths EMNLP 2023 On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation ICLR 2023 Efficient Algorithms for Recognizing Weighted Tree-Adjoining Languages EMNLP 2023 On the Representational Capacity of Recurrent Neural Language Models EMNLP 2023 On the Intersection of Context-Free and Regular Languages EACL 2023 An Exploration of Left-Corner Transformations EMNLP 2023 A Measure-Theoretic Characterization of Tight Language Models ACL 2023 Quantifying the redundancy between prosody and text EMNLP 2023 Recurrent Neural Language Models as Probabilistic Finite-state Automata EMNLP 2023 The Ordered Matrix Dirichlet for State-Space Models AISTATS 2023 Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora EMNLP 2023 Controlled Text Generation with Natural Language Instructions ICML 2023 Structured Voronoi Sampling NIPS 2023 Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora CONLL 2023 Sentiment as an Ordinal Latent Variable EACL 2023 LEACE: Perfect linear concept erasure in closed form NIPS 2023 Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective EMNLP 2023 A Latent-Variable Model for Intrinsic Probing AAAI 2023 On the Efficacy of Sampling Adapters ACL 2023 Efficient Semiring-Weighted Earley Parsing ACL 2023 An Ordinal Latent Variable Model of Conflict Intensity ACL 2023 Tokenization and the Noiseless Channel ACL 2023 Convergence and Diversity in the Control Hierarchy ACL 2023 Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels ACL 2023 Log-linear Guardedness and its Implications ACL 2023 Probing as Quantifying Inductive Bias ACL 2022 Probing for the Usage of Grammatical Number ACL 2022 Analyzing Wrap-Up Effects through an Information-Theoretic Lens ACL 2022 On the probability–quality paradox in language generation ACL 2022 Estimating the Entropy of Linguistic Distributions ACL 2022 Probing via Prompting NAACL 2022 SIGMORPHON–UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection NAACL 2022 The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes NAACL 2022 BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation NAACL 2022 Mutual Information Alleviates Hallucinations in Abstractive Summarization EMNLP 2022 Adversarial Concept Erasure in Kernel Space EMNLP 2022 Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models NAACL 2022 A Structured Span Selector NAACL 2022 Equivariant Transduction through Invariant Alignment COLING 2022 Benchmarking Compositionality with Formal Languages COLING 2022 Exact Paired-Permutation Testing for Structured Test Statistics NAACL 2022 Algorithms for Acyclic Weighted Finite-State Automata with Failure Arcs EMNLP 2022 On Parsing as Tagging EMNLP 2022 Algorithms for Weighted Pushdown Automata EMNLP 2022 The Architectural Bottleneck Principle EMNLP 2022 Autoregressive Structured Prediction with Language Models EMNLP 2022 The SIGMORPHON 2022 Shared Task on Morpheme Segmentation NAACL 2022 On the Machine Learning of Ethical Judgments from Natural Language NAACL 2022 Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing NAACL 2021 Examining the Inductive Bias of Neural Language Models with Artificial Languages ACL 2021 On Finding the K-best Non-projective Dependency Trees ACL 2021 A Cognitive Regularizer for Language Modeling ACL 2021 Language Model Evaluation Beyond Perplexity ACL 2021 Determinantal Beam Search ACL 2021 Is Sparse Attention more Interpretable? ACL 2021 Higher-order Derivatives of Weighted Finite-state Machines ACL 2021 Modeling the Unigram Distribution ACL 2021 SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages ACL 2021 Disambiguatory Signals are Stronger in Word-initial Positions EACL 2021 Searching for Search Errors in Neural Morphological Inflection EACL 2021 Applying the Transformer to Character-level Transduction EACL 2021 Conditional Poisson Stochastic Beams EMNLP 2021 A surprisal–duration trade-off across and within the world’s languages EMNLP 2021 Revisiting the Uniform Information Density Hypothesis EMNLP 2021 A Bayesian Framework for Information-Theoretic Probing EMNLP 2021 Classifying Dyads for Militarized Conflict Analysis EMNLP 2021 On Homophony and Rényi Entropy EMNLP 2021 Efficient Sampling of Dependency Structure EMNLP 2021 Searching for More Efficient Dynamic Programs EMNLP 2021 A Plug-and-Play Method for Controlled Text Generation EMNLP 2021 Examining the Inductive Bias of Neural Language Models with Artificial Languages IJCNLP 2021 On Finding the K-best Non-projective Dependency Trees IJCNLP 2021 A Cognitive Regularizer for Language Modeling IJCNLP 2021 Language Model Evaluation Beyond Perplexity IJCNLP 2021 Determinantal Beam Search IJCNLP 2021 Is Sparse Attention more Interpretable? IJCNLP 2021 Higher-order Derivatives of Weighted Finite-state Machines IJCNLP 2021 Modeling the Unigram Distribution IJCNLP 2021 SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages IJCNLP 2021 A Non-Linear Structural Probe NAACL 2021 What About the Precedent: An Information-Theoretic Analysis of Common Law NAACL 2021 Finding Concept-specific Biases in Form–Meaning Associations NAACL 2021 How (Non-)Optimal is the Lexicon? NAACL 2021 SIGTYP 2021 Shared Task: Robust Spoken Language Identification NAACL 2021 Conditional Poisson Stochastic Beam Search EMNLP 2021 Efficient Sampling of Dependency Structures EMNLP 2021 SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ACL 2020 Morphologically Aware Word-Level Translation COLING 2020 If beam search is the answer, what was the question? EMNLP 2020 Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation EMNLP 2020 Pareto Probing: Trading Off Accuracy for Complexity EMNLP 2020 Speakers Fill Lexical Semantic Gaps with Context EMNLP 2020 Investigating Cross-Linguistic Adjective Ordering Tendencies with a Latent-Variable Model EMNLP 2020 Please Mind the Root: Decoding Arborescences for Dependency Parsing EMNLP 2020 Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions EMNLP 2020 SIGTYP 2020 Shared Task: Prediction of Typological Features EMNLP 2020 It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information ACL 2020 A Corpus for Large-Scale Phonetic Typology ACL 2020 Information-Theoretic Probing for Linguistic Structure ACL 2020 Predicting Declension Class from Form and Meaning ACL 2020 Intrinsic Probing through Dimension Selection EMNLP 2020 Generalized Entropy Regularization or: There’s Nothing Special about Label Smoothing ACL 2020 A Tale of a Probe and a Parser ACL 2020 The Paradigm Discovery Problem ACL 2020 Metaphor Detection using Context and Concreteness ACL 2020 What Kind of Language Is Hard to Language-Model? ACL 2019 Weird Inflects but OK: Making Sense of Morphological Generation Errors CONLL 2019 Don’t Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction IJCNLP 2019 Towards Zero-shot Language Modeling IJCNLP 2019 It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution IJCNLP 2019 Examining Gender Bias in Languages with Grammatical Gender IJCNLP 2019 Quantifying the Semantic Core of Gender Systems IJCNLP 2019 On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study ACL 2019 Uncovering Probabilistic Implications in Typological Knowledge Bases ACL 2019 Meaning to Form: Measuring Systematicity as Information ACL 2019 Unsupervised Discovery of Gendered Language through Latent-Variable Modeling ACL 2019 Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology ACL 2019 Exact Hard Monotonic Attention for Character-Level Transduction ACL 2019 The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection ACL 2019 Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology ACL 2019 Gender Bias in Contextualized Word Embeddings NAACL 2019 Combining Sentiment Lexica with a Multi-View Variational Autoencoder NAACL 2019 A Simple Joint Model for Improved Contextual Neural Lemmatization NAACL 2019 A Probabilistic Generative Model of Linguistic Typology NAACL 2019 Contextualization of Morphological Inflection NAACL 2019 On the Idiosyncrasies of the Mandarin Chinese Classifier System NAACL 2019 Rethinking Phonotactic Complexity ACL 2019 Proceedings of TyP-NLP: The First Workshop on Typology for Polyglot NLP ACL 2019 Morphological Irregularity Correlates with Frequency ACL 2019 Quantifying the Semantic Core of Gender Systems EMNLP 2019 Examining Gender Bias in Languages with Grammatical Gender EMNLP 2019 It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution EMNLP 2019 Towards Zero-shot Language Modeling EMNLP 2019 Don’t Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction EMNLP 2019 Are All Languages Equally Hard to Language-Model? NAACL 2018 Unsupervised Disambiguation of Syncretism in Inflected Lexicons NAACL 2018 A Structured Variational Autoencoder for Contextual Morphological Inflection ACL 2018 A Deep Generative Model of Vowel Formant Typology NAACL 2018 Marrying Universal Dependencies and Universal Morphology EMNLP 2018 A Discriminative Latent-Variable Model for Bilingual Lexicon Induction EMNLP 2018 Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction CONLL 2018 Proceedings of the CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection CONLL 2018 The CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection CONLL 2018 Hard Non-Monotonic Attention for Character-Level Transduction EMNLP 2018 Context-Aware Prediction of Derivational Word-forms EACL 2017 Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis EACL 2017 Cross-lingual Character-Level Neural Morphological Tagging EMNLP 2017 Morphological Analysis of the Dravidian Language Family EACL 2017 Neural Graphical Models over Strings for Principal Parts Morphological Paradigm Completion EACL 2017 Paradigm Completion for Derivational Morphology EMNLP 2017 CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages CONLL 2017 Low-Resource Named Entity Recognition with Cross-lingual, Character-Level Neural Conditional Random Fields IJCNLP 2017 One-Shot Neural Cross-Lingual Transfer for Paradigm Completion ACL 2017 Probabilistic Typology: Deep Generative Models of Vowel Inventories ACL 2017 Neural Multi-Source Morphological Reinflection EACL 2017 A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax EACL 2017 Morphological Segmentation Inside-Out EMNLP 2016 A Joint Model of Orthography and Morphological Segmentation NAACL 2016 Neural Morphological Analysis: Encoding-Decoding Canonical Segments EMNLP 2016 Morphological Smoothing and Extrapolation of Word Embeddings ACL 2016 Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity EMNLP 2016 Weighting Finite-State Transductions With Neural Context NAACL 2016 Dual Decomposition Inference for Graphical Models over Strings EMNLP 2015 Labeled Morphological Segmentation with Semi-Markov Models CONLL 2015 Penalized Expectation Propagation for Graphical Models over Strings NAACL 2015 Morphological Word-Embeddings NAACL 2015 Joint Lemmatization and Morphological Tagging with Lemming EMNLP 2015 Stochastic Contextual Edit Distance and Probabilistic FSTs ACL 2014