Noah A. Smith
Artificial Intelligence · 2003–2024
A researcher in the Science corpus: 141 papers; trusts 4,421 researchers and is trusted by 7,699 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 3,895 citations into it; #162 of 36,961 by trust here, #105 by citations
- Natural Language Processing — 2,240 citations into it; #44 of 5,725 by trust here, #46 by citations
- Computer Vision and Pattern Recognition — 1,233 citations into it; #2,785 of 21,973 by trust here, #954 by citations
- Evaluation & Benchmarks — 721 citations into it; #85 of 3,155 by trust here, #86 by citations
- Large Language Models — 469 citations into it; #105 of 810 by trust here, #103 by citations
- Safety, Robustness & Interpretability — 321 citations into it; #97 of 2,259 by trust here, #71 by citations
- Model Architectures — 316 citations into it; #318 of 2,288 by trust here, #335 by citations
- Representation & Self-Supervised Learning — 310 citations into it; #494 of 3,156 by trust here, #361 by citations
Whom Noah A. Smith trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Alex Graves
- Kaiming He
- Richard Socher
- Yann LeCun
- Sepp Hochreiter
Who trusts Noah A. Smith overall
- Percy Liang
- Yoav Goldberg
- Yonatan Belinkov
- Dirk Hovy
- Graham Neubig
- Mohit Bansal
- Aliaksei Severyn
- Chris Dyer
- Kyunghyun Cho
- Yulia Tsvetkov
Papers from Noah A. Smith's perspective
Ordered by how strongly the researchers Noah A. Smith trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet classification with deep convolutional neural networks
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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)
- Gradient-based learning applied to document recognition
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Annotation Artifacts in Natural Language Inference Data (2018) — 1,309 citations
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models (2020) — 1,775 citations
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory (2015) — 818 citations
- Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (2020) — 3,085 citations
- A Simple, Fast, and Effective Reparameterization of IBM Model 2 (2013) — 1,111 citations
- The Risk of Racial Bias in Hate Speech Detection (2019) — 1,043 citations
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2016) — 1,401 citations
- Self-Instruct: Aligning Language Models with Self-Generated Instructions (2022) — 3,444 citations
- Recurrent Neural Network Grammars (2016) — 551 citations
- Social Bias Frames: Reasoning about Social and Power Implications of Language (2019) — 640 citations
- Linguistic Knowledge and Transferability of Contextual Representations (2019) — 833 citations
- Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping (2020) — 739 citations
- Contrastive Estimation: Training Log-Linear Models on Unlabeled Data (2005) — 381 citations
- Knowledge Enhanced Contextual Word Representations (2019) — 729 citations
- To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks (2019) — 485 citations
- Evaluating Gender Bias in Machine Translation (2019) — 471 citations
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation (2021) — 1,298 citations
- Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection (2021) — 408 citations
- What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA (2007) — 475 citations
- Random Feature Attention (2021) — 447 citations