| 2026 | CoNLL | Evaluating Humanlike Memory Effects in Transformers Using Item Recognition Tasks. | Christian Clark, William Schuler |
| 2026 | EACL | Surprisal from Larger Transformer-based Language Models Predicts fMRI Data More Poorly. | Yi-Chien Lin, William Schuler |
| 2025 | ACL | The Impact of Token Granularity on the Predictive Power of Language Model Surprisal. | Byung-Doh Oh, William Schuler |
| 2025 | ACL | The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage. | Byung-Doh Oh, Hongao Zhu, William Schuler |
| 2025 | COLING | Linear Recency Bias During Training Improves Transformers' Fit to Reading Times. | Christian Clark, Byung-Doh Oh, William Schuler |
| 2025 | IJCNLP | How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor? | Christian Clark, Byung-Doh Oh, William Schuler |
| 2024 | COLING | Categorial Grammar Induction with Stochastic Category Selection. | Christian Clark, William Schuler |
| 2024 | EACL | Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times. | Byung-Doh Oh, Shisen Yue, William Schuler |
| 2024 | EMNLP | Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities. | Byung-Doh Oh, William Schuler |
| 2023 | ACL | Categorial grammar induction from raw data. | Christian Clark, William Schuler |
| 2023 | ACL | Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions. | Byung-Doh Oh, William Schuler |
| 2023 | EMNLP | Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens. | Byung-Doh Oh, William Schuler |
| 2023 | SIGdial | Bootstrapping a Conversational Guide for Colonoscopy Prep. | Pulkit Arya, Madeleine Bloomquist, Subhankar Chakraborty, Andrew Perrault, William Schuler, Eric Fosler-Lussier, Michael White |
| 2022 | EMNLP | Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal. | Byung-Doh Oh, William Schuler |
| 2021 | ACL | Surprisal Estimators for Human Reading Times Need Character Models. | Byung-Doh Oh, Christian Clark, William Schuler |
| 2021 | EMNLP | Coreference-aware Surprisal Predicts Brain Response. | Evan Jaffe, Byung-Doh Oh, William Schuler |
| 2021 | EMNLP | Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages. | Lifeng Jin, Byung-Doh Oh, William Schuler |
| 2020 | COLING | Coreference information guides human expectations during natural reading. | Evan Jaffe, Cory Shain, William Schuler |
| 2020 | IJCNLP | Grounded PCFG Induction with Images. | Lifeng Jin, William Schuler |
| 2020 | LREC | A Corpus of Encyclopedia Articles with Logical Forms. | Nathan Rasmussen, William Schuler |
| 2019 | ACL | Unsupervised Learning of PCFGs with Normalizing Flow. | Lifeng Jin, Finale Doshi-Velez, Timothy Miller, Lane Schwartz, William Schuler |
| 2019 | ACL | Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction. | Lifeng Jin, William Schuler |
| 2018 | EMNLP | Depth-bounding is effective: Improvements and Evaluation of Unsupervised PCFG Induction. | Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz |
| 2018 | EMNLP | Deconvolutional time series regression: A technique for modeling temporally diffuse effects. | Cory Shain, William Schuler |
| 2018 | LREC | Test Sets for Chinese Nonlocal Dependency Parsing. | Manjuan Duan, William Schuler |
| 2017 | CogSci | Approximations of Predictive Entropy Correlate with Reading Times. | Marten van Schijndel, William Schuler |
| 2016 | COLING | Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input. | Cory Shain, William Bryce, Lifeng Jin, Victoria Krakovna, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz |
| 2015 | NAACL | A Comparison of Word Similarity Performance Using Explanatory and Non-explanatory Texts. | Lifeng Jin, William Schuler |
| 2015 | NAACL | Hierarchic syntax improves reading time prediction. | Marten van Schijndel, William Schuler |
| 2014 | CogSci | Frequency effects in the processing of unbounded dependencies. | Marten van Schijndel, William Schuler, Peter W. Culicover |
| 2013 | NAACL | An Analysis of Frequency- and Memory-Based Processing Costs. | Marten van Schijndel, William Schuler |
| 2012 | COLING | Accurate Unbounded Dependency Recovery using Generalized Categorial Grammars. | Luan Nguyen, Marten van Schijndel, William Schuler |
| 2011 | ACL | A Pronoun Anaphora Resolution System based on Factorial Hidden Markov Models. | Dingcheng Li, Tim Miller, William Schuler |
| 2011 | ACL | Incremental Syntactic Language Models for Phrase-based Translation. | Lane Schwartz, Chris Callison-Burch, William Schuler, Stephen T. Wu |
| 2011 | CogSci | Effects of Filler-gap Dependencies Working Memory Requirements for Parsing. | William Schuler |
| 2010 | ACL | Complexity Metrics in an Incremental Right-Corner Parser. | Stephen T. Wu, Asaf Bachrach, Carlos Cardenas, William Schuler |
| 2009 | ACL | Parsing Speech Repair without Specialized Grammar Symbols. | Tim Miller, Luan Nguyen, William Schuler |
| 2009 | IUI | Positive effects of redundant descriptions in an interactive semantic speech interface. | Lane Schwartz, Luan Nguyen, Andrew Exley, William Schuler |
| 2009 | NAACL | Positive Results for Parsing with a Bounded Stack using a Model-Based Right-Corner Transform. | William Schuler |
| 2008 | ACL | A Unified Syntactic Model for Parsing Fluent and Disfluent Speech. | Tim Miller, William Schuler |
| 2008 | COLING | A Syntactic Time-Series Model for Parsing Fluent and Disfluent Speech. | Tim Miller, William Schuler |
| 2008 | COLING | Toward a Psycholinguistically-Motivated Model of Language Processing. | William Schuler, Samir AbdelRahman, Tim Miller, Lane Schwartz |
| 2008 | ICASSP | Referential semantic language modeling for data-poor domains. | Stephen T. Wu, Lane Schwartz, William Schuler |
| 2008 | IUI | Exploiting referential context in spoken language interfaces for data-poor domains. | Stephen T. Wu, Lane Schwartz, William Schuler |
| 2007 | HRI | Elements of a spoken language programming interface for robots. | Tim Miller, Andrew Exley, William Schuler |
| 2006 | Interspeech | Dynamic evidence models in a DBN phone recognizer. | William Schuler, Tim Miller, Stephen T. Wu, Andrew Exley |
| 2005 | Interspeech | Integrating denotational meaning into a DBN language model. | William Schuler, Tim Miller |
| 2003 | ACL | Using Model-Theoretic Semantic Interpretation to Guide Statistical Parsing and Word Recognition in a Spoken Language Interface. | William Schuler |
| 2002 | COLING | Interleaved Semantic Interpretation in Environment-based Parsing. | William Schuler |
| 2001 | ACL | Computational Properties of Environment-based Disambiguation. | William Schuler |
| 2000 | ACL | Multi-Component TAG and Notions of Formal Power. | William Schuler, David Chiang, Mark Dras |
| 2000 | AMTA | A Machine Translation System from English to American Sign Language. | Liwei Zhao, Karin Kipper, William Schuler, Christian Vogler, Norman I. Badler, Martha Stone Palmer |
| 1999 | ACL | Preserving Semantic Dependencies in Synchronous Tree Adjoining Grammar. | William Schuler |
| 1998 | ACL | Restrictions on Tree Adjoining Languages. | Giorgio Satta, William Schuler |