Hal Daumé Iii
Artificial Intelligence · 2004–2022
A researcher in the Science corpus: 54 papers; trusts 2,500 researchers and is trusted by 8,875 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,241 citations into it; #262 of 36,961 by trust here, #471 by citations
- Natural Language Processing — 639 citations into it; #272 of 5,725 by trust here, #269 by citations
- Computer Vision and Pattern Recognition — 264 citations into it; #455 of 21,973 by trust here, #1,259 by citations
- Safety, Robustness & Interpretability — 244 citations into it; #661 of 2,259 by trust here, #237 by citations
- Language and Linguistics — 141 citations into it
- Representation & Self-Supervised Learning — 131 citations into it; #52 of 3,156 by trust here, #202 by citations
- Evaluation & Benchmarks — 124 citations into it; #1,807 of 3,155 by trust here, #540 by citations
- Sociology and Political Science — 104 citations into it
Whom Hal Daumé Iii trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Diederik P. Kingma
- Alex Krizhevsky
- Michael Collins
- Yann LeCun
- Kaiming He
- Richard Socher
- Sepp Hochreiter
Who trusts Hal Daumé Iii overall
- Judy Hoffman
- Mohammad Rostami
- Qiang Yang
- Trevor Darrell
- Lixin Duan
- Garrett Wilson
- Kate Saenko
- Gabriella Csurka
- Yoshua Bengio
- Kristen Grauman
Papers from Hal Daumé Iii's perspective
Ordered by how strongly the researchers Hal Daumé Iii 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)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Midge: Generating Image Descriptions From Computer Vision Detections (2012) — 495 citations
- Search-based structured prediction (2009) — 602 citations
- Datasheets for datasets (2018) — 3,178 citations
- Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020) — 1,755 citations
- Corpus-Guided Sentence Generation of Natural Images (2011) — 423 citations
- Frustratingly Easy Domain Adaptation (2007) — 1,845 citations
- Deep Unordered Composition Rivals Syntactic Methods for Text Classification (2015) — 842 citations
- A Neural Network for Factoid Question Answering over Paragraphs (2014) — 375 citations
- Learning to Search Better than Your Teacher (2015) — 238 citations
- Understanding and predicting importance in images (2012) — 164 citations
- Learning Task Grouping and Overlap in Multi-task Learning (2012) — 541 citations
- Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task (2017) — 95 citations
- Generalized Multiview Analysis: A discriminative latent space (2012) — 745 citations
- Domain Adaptation for Statistical Classifiers (2006) — 920 citations
- Non-Monotonic Sequential Text Generation (2019) — 143 citations
- Structure compilation: trading structure for features (2008) — 88 citations
- Bayesian Multitask Learning with Latent Hierarchies (2009) — 133 citations
- Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback (2017) — 145 citations
- Hierarchical Imitation and Reinforcement Learning (2018) — 221 citations
- Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information (2018) — 227 citations