Jason Eisner
Artificial Intelligence · 1996–2022
A researcher in the Science corpus: 25 papers; trusts 847 researchers and is trusted by 2,766 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 317 citations into it; #470 of 36,961 by trust here, #2,309 by citations
- Natural Language Processing — 172 citations into it; #286 of 5,725 by trust here, #767 by citations
- Computer Vision and Pattern Recognition — 47 citations into it; #3,870 of 21,973 by trust here, #4,813 by citations
- Large Language Models — 32 citations into it; #102 of 810 by trust here, #490 by citations
- Probabilistic & Bayesian Methods — 29 citations into it; #304 of 1,526 by trust here, #420 by citations
- Optimization & Training — 27 citations into it; #451 of 2,605 by trust here, #1,009 by citations
- Language and Linguistics — 22 citations into it; #41 of 3,482 by trust here, #244 by citations
- Model Architectures — 20 citations into it
Whom Jason Eisner trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Andrew McCallum
- Michael Collins
- Diederik P. Kingma
- James K. Baker
- Yann LeCun
- Yoshua Bengio
- Ilya Sutskever
- John D. Lafferty
- Franz Joseph Och
Who trusts Jason Eisner overall
- Noah A. Smith
- Ryan T. McDonald
- Michael Collins
- Joakim Nivre
- Kevin Gimpel
- Daniel Klein
- David Chiang
- Yoon Kim
- Yoshua Bengio
- David A. Smith
Papers from Jason Eisner's perspective
Ordered by how strongly the researchers Jason Eisner 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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)
- 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
- Contrastive Estimation: Training Log-Linear Models on Unlabeled Data (2005) — 381 citations
- Learning How to Ask: Querying LMs with Mixtures of Soft Prompts (2021) — 602 citations
- Empirical Risk Minimization of Graphical Model Parameters Given Approximate Inference, Decoding, and Model Structure (2011) — 132 citations
- Three New Probabilistic Models for Dependency Parsing: An Exploration (1996)
- Modeling Annotators: A Generative Approach to Learning from Annotator Rationales (2008) — 175 citations
- Quasi-Synchronous Grammars: Alignment by Soft Projection of Syntactic Dependencies (2006) — 113 citations
- First- and Second-Order Expectation Semirings with Applications to Minimum-Risk Training on Translation Forests (2009) — 161 citations
- Constrained Language Models Yield Few-Shot Semantic Parsers (2021) — 247 citations
- Task-Oriented Dialogue as Dataflow Synthesis (2020) — 176 citations
- Dependency Parsing by Belief Propagation (2008) — 163 citations
- Efficient Parsing for Bilexical Context-Free Grammars and Head Automaton Grammars (1999)
- Contrastive Decoding: Open-ended Text Generation as Optimization (2022) — 688 citations
- Approximation-Aware Dependency Parsing by Belief Propagation (2015) — 36 citations
- Graphical Models over Multiple Strings (2009) — 44 citations
- Parameter Estimation for Probabilistic Finite-State Transducers (2002) — 213 citations
- Are All Languages Equally Hard to Language-Model? (2018) — 116 citations
- Minimum-Risk Training of Approximate CRF-Based NLP Systems (2012) — 32 citations
- Learning to Search in Branch and Bound Algorithms (2014) — 279 citations
- Inside-Outside and Forward-Backward Algorithms Are Just Backprop (tutorial paper) (2016) — 89 citations
- Dual Decomposition Inference for Graphical Models over Strings (2015) — 7 citations