Hanna M. Wallach
Artificial Intelligence · 2002–2021
A researcher in the Science corpus: 31 papers; trusts 452 researchers and is trusted by 1,423 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 507 citations into it; #818 of 36,961 by trust here, #923 by citations
- Safety, Robustness & Interpretability — 310 citations into it; #221 of 2,259 by trust here, #100 by citations
- Natural Language Processing — 198 citations into it; #720 of 5,725 by trust here, #674 by citations
- Safety Research — 151 citations into it; #247 of 5,835 by trust here, #112 by citations
- Sociology and Political Science — 144 citations into it; #6,501 of 22,891 by trust here, #2,011 by citations
- AI Ethics, Fairness & Society — 98 citations into it; #83 of 496 by trust here, #52 by citations
- Computer Vision and Pattern Recognition — 83 citations into it; #7,396 of 21,973 by trust here, #14,470 by citations
- Social Sciences & Humanities — 82 citations into it
Whom Hanna M. Wallach trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Lawrence R. Rabiner
- Andrew McCallum
- John D. Lafferty
- T. Griffiths
- Radford M. Neal
- Stephen Della Pietra
- Frederick Jelinek
- Robert Malouf
- Geoffrey E. Hinton
- Fernando C Pereira
Who trusts Hanna M. Wallach overall
- Andrew McCallum
- Charu C. Aggarwal
- Charles Sutton
- Ruslan Salakhutdinov
- David Mimno
- Ivan Titov
- David M. Blei
- Mark W. Schmidt
- Fei Sha
- Diarmuid Ó Séaghdha
Papers from Hanna M. Wallach's perspective
Ordered by how strongly the researchers Hanna M. Wallach 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
- Learning Multiple Layers of Features from Tiny Images
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Datasheets for datasets (2018) — 3,178 citations
- Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020) — 1,755 citations
- Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets (2021) — 389 citations
- Measurement and Fairness (2019) — 535 citations
- A Reductions Approach to Fair Classification (2018) — 1,292 citations
- Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting (2019) — 587 citations
- Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs (2021) — 98 citations
- Topic modeling: beyond bag-of-words (2006) — 1,250 citations
- Learning the Structure of Deep Sparse Graphical Models (2009) — 90 citations
- Rethinking LDA: Why Priors Matter (2009) — 775 citations
- Manipulating and Measuring Model Interpretability (2018) — 848 citations
- Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology (2019) — 344 citations
- Efficient Training of Conditional Random Fields (2002) — 178 citations
- What’s in a Name? Reducing Bias in Bios without Access to Protected Attributes (2019) — 86 citations
- Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning (2020) — 609 citations
- Quantifying the Semantic Core of Gender Systems (2019) — 19 citations
- Unsupervised Discovery of Gendered Language through Latent-Variable Modeling (2019) — 56 citations
- Understanding the Effect of Accuracy on Trust in Machine Learning Models (2019) — 599 citations
- Auditing Search Engines for Differential Satisfaction Across Demographics (2017) — 90 citations
- Fairlearn: A toolkit for assessing and improving fairness in AI (2020) — 455 citations