Doug Downey
Artificial Intelligence · 2004–2022
A researcher in the Science corpus: 13 papers; trusts 778 researchers and is trusted by 160 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 343 citations into it; #2,701 of 36,961 by trust here, #2,043 by citations
- Natural Language Processing — 238 citations into it; #1,241 of 5,725 by trust here, #1,116 by citations
- Computer Vision and Pattern Recognition — 91 citations into it; #14,369 of 21,973 by trust here, #6,060 by citations
- Evaluation & Benchmarks — 68 citations into it
- Large Language Models — 52 citations into it; #626 of 810 by trust here, #375 by citations
- Information Systems — 46 citations into it; #3,014 of 9,233 by trust here, #1,033 by citations
- Representation & Self-Supervised Learning — 30 citations into it; #2,524 of 3,156 by trust here, #2,815 by citations
- Information Retrieval & Search — 25 citations into it; #223 of 1,022 by trust here, #333 by citations
Whom Doug Downey trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Diederik P. Kingma
- Alex Krizhevsky
- Richard Socher
- Alex Graves
- Yann LeCun
- Oriol Vinyals
- Kaiming He
Who trusts Doug Downey overall
- Bhavana Dalvi
- Greg Durrett
- Fabian M. Suchanek
- Zhaochen Guo
- Daniel S. Weld
- Oren Etzioni
- Xiao Ling
- Michele Banko
- Avirup Sil
- Dan Roth
Papers from Doug Downey's perspective
Ordered by how strongly the researchers Doug Downey trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- 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
- Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (2020) — 3,085 citations
- Abductive Commonsense Reasoning (2019) — 542 citations
- Local and Global Algorithms for Disambiguation to Wikipedia (2011) — 755 citations
- Unsupervised named-entity extraction from the Web: An experimental study (2005) — 1,295 citations
- Web-scale information extraction in knowitall: (preliminary results) (2004) — 931 citations
- Few-Shot Self-Rationalization with Natural Language Prompts (2021) — 119 citations
- Construction of the Literature Graph in Semantic Scholar (2018) — 442 citations
- G-DAug: Generative Data Augmentation for Commonsense Reasoning (2020) — 92 citations
- SPECTER: Document-level Representation Learning using Citation-informed Transformers (2020) — 853 citations
- Extracting Commonsense Properties from Embeddings with Limited Human Guidance (2018) — 21 citations
- Methods for exploring and mining tables on Wikipedia (2013) — 110 citations
- Don’t Say What You Don’t Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search (2022) — 36 citations
- Just Add Functions: A Neural-Symbolic Language Model (2019) — 11 citations