Willem H. Zuidema
Artificial Intelligence · 2014–2022
A researcher in the Science corpus: 13 papers; trusts 941 researchers and is trusted by 336 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 321 citations into it; #1,760 of 36,961 by trust here, #4,491 by citations
- Natural Language Processing — 180 citations into it; #723 of 5,725 by trust here, #1,403 by citations
- Safety, Robustness & Interpretability — 94 citations into it; #810 of 2,259 by trust here, #857 by citations
- Computer Vision and Pattern Recognition — 68 citations into it
- Model Architectures — 54 citations into it; #258 of 2,288 by trust here, #678 by citations
- Representation & Self-Supervised Learning — 34 citations into it
- Large Language Models — 32 citations into it
- Cognitive Neuroscience — 21 citations into it; #6,903 of 11,026 by trust here, #8,509 by citations
Whom Willem H. Zuidema trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard Socher
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Christopher D. Manning
- Sepp Hochreiter
- Ilya Sutskever
- Alex Krizhevsky
- Yann LeCun
- Tomas Mikolov
Who trusts Willem H. Zuidema overall
- Yonatan Belinkov
- Yoav Goldberg
- Dieuwke Hupkes
- John Hewitt
- Eliyahu Kiperwasser
- Hila Chefer
- Grzegorz Chrupała
- Abhilasha Ravichander
- Mostafa Dehghani
- Tal Linzen
Papers from Willem H. Zuidema's perspective
Ordered by how strongly the researchers Willem H. Zuidema trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Visualisation and 'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure (2017) — 304 citations
- The Inside-Outside Recursive Neural Network model for Dependency Parsing (2014) — 73 citations
- Quantifying Attention Flow in Transformers (2020) — 1,293 citations
- Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information (2018) — 202 citations
- Transferring Inductive Biases through Knowledge Distillation (2020) — 72 citations
- The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization (2015) — 37 citations
- Diagnostic Classifiers Revealing how Neural Networks Process Hierarchical Structure (2016) — 47 citations
- Analysing Neural Language Models: Contextual Decomposition Reveals Default Reasoning in Number and Gender Assignment (2019) — 42 citations
- Visualisation and 'Diagnostic Classifiers' Reveal how Recurrent and Recursive Neural Networks Process Hierarchical Structure (Extended Abstract) (2018) — 25 citations
- Blackbox Meets Blackbox: Representational Similarity & Stability Analysis of Neural Language Models and Brains (2019) — 85 citations
- The Birth of Bias: A case study on the evolution of gender bias in an English language model (2022) — 24 citations
- Undesirable biases in NLP: Averting a crisis of measurement (2022) — 8 citations
- Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization (2019) — 18 citations