| 2025 | ICLR | PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs. | Oskar van der Wal, Pietro Lesci, Max Mller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem H. Zuidema, Stella Biderman |
| 2025 | Interspeech | What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training. | Marianne de Heer Kloots, Hosein Mohebbi, Charlotte Pouw, Gaofei Shen, Willem H. Zuidema, Martijn Bentum |
| 2024 | ACL | Do Language Models Exhibit Human-like Structural Priming Effects? | Jaap Jumelet, Willem H. Zuidema, Arabella Sinclair |
| 2024 | CogSci | Language Models That Accurately Represent Syntactic Structure Exhibit Higher Representational Similarity To Brain Activity. | Abraham Jacob Fresen, Rochelle Choenni, Micha Heilbron, Willem H. Zuidema, Marianne de Heer Kloots |
| 2024 | Interspeech | Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0. | Marianne de Heer Kloots, Willem H. Zuidema |
| 2024 | NAACL | DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers. | Anna Langedijk, Hosein Mohebbi, Gabriele Sarti, Willem H. Zuidema, Jaap Jumelet |
| 2023 | ACL | Feature Interactions Reveal Linguistic Structure in Language Models. | Jaap Jumelet, Willem H. Zuidema |
| 2023 | EACL | Quantifying Context Mixing in Transformers. | Hosein Mohebbi, Willem H. Zuidema, Grzegorz Chrupala, Afra Alishahi |
| 2023 | EMNLP | Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution. | Jaap Jumelet, Willem H. Zuidema |
| 2023 | EMNLP | Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers. | Hosein Mohebbi, Grzegorz Chrupala, Willem H. Zuidema, Afra Alishahi |
| 2020 | ACL | Quantifying Attention Flow in Transformers. | Samira Abnar, Willem H. Zuidema |
| 2020 | COLING | DoLFIn: Distributions over Latent Features for Interpretability. | Phong Le, Willem H. Zuidema |
| 2019 | CoNLL | Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment. | Jaap Jumelet, Willem H. Zuidema, Dieuwke Hupkes |
| 2018 | EMNLP | Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information. | Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes, Willem H. Zuidema |
| 2018 | IJCAI | Visualisation and 'Diagnostic Classifiers' Reveal how Recurrent and Recursive Neural Networks Process Hierarchical Structure (Extended Abstract). | Dieuwke Hupkes, Willem H. Zuidema |
| 2017 | CogSci | Segmentation as Retention and Recognition: the R&R model. | Raquel G. Alhama, Willem H. Zuidema |
| 2015 | EMNLP | The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization. | Phong Le, Willem H. Zuidema |
| 2015 | NAACL | Unsupervised Dependency Parsing: Let's Use Supervised Parsers. | Phong Le, Willem H. Zuidema |
| 2014 | EMNLP | The Inside-Outside Recursive Neural Network model for Dependency Parsing. | Phong Le, Willem H. Zuidema |
| 2013 | ACL | Learning from errors: Using vector-based compositional semantics for parse reranking. | Phong Le, Willem H. Zuidema, Remko Scha |
| 2013 | CogSci | Context-freeness Revisited. | Willem H. Zuidema |
| 2012 | COLING | Learning Compositional Semantics for Open Domain Semantic Parsing. | Phong Le, Willem H. Zuidema |
| 2011 | CogSci | Episodic grammar: a computational model of the interaction between episodic and semantic memory in language processing. | Gideon Borensztajn, Willem H. Zuidema |
| 2011 | EMNLP | Accurate Parsing with Compact Tree-Substitution Grammars: Double-DOP. | Federico Sangati, Willem H. Zuidema |
| 2010 | LREC | Efficiently Extract Recurring Tree Fragments from Large Treebanks. | Federico Sangati, Willem H. Zuidema, Rens Bod |
| 2009 | EACL | Unsupervised Methods for Head Assignments. | Federico Sangati, Willem H. Zuidema |
| 2007 | EMNLP | Parsimonious Data-Oriented Parsing. | Willem H. Zuidema |
| 2006 | CoNLL | What are the Productive Units of Natural Language Grammar? A DOP Approach to the Automatic Identification of Constructions. | Willem H. Zuidema |
| 2006 | EACL | Theoretical Evaluation of Estimation Methods for Data-Oriented Parsing. | Willem H. Zuidema |