Georgiana Dinu

Artificial Intelligence · 2013–2021

A researcher in the Science corpus: 6 papers; trusts 227 researchers and is trusted by 113 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 115 citations into it; #2,332 of 35,345 by trust here, #4,797 by citations
• Natural Language Processing — 106 citations into it; #968 of 5,688 by trust here, #1,418 by citations
• Representation & Self-Supervised Learning — 39 citations into it; #696 of 3,145 by trust here, #972 by citations
• Computer Vision and Pattern Recognition — 34 citations into it; #4,316 of 21,575 by trust here, #4,926 by citations
• Model Architectures — 16 citations into it
• Safety, Robustness & Interpretability — 14 citations into it
• Evaluation & Benchmarks — 8 citations into it
• Multimodal Learning — 8 citations into it

Whom Georgiana Dinu trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Tomas Mikolov
2. Richard Socher
3. Geoffrey E. Hinton
4. Ilya Sutskever
5. Alex Krizhevsky
6. Yoshua Bengio
7. Marco Baroni
8. Diederik P. Kingma
9. Yann LeCun
10. Quoc V. Le

Who trusts Georgiana Dinu overall

1. Mikel Artetxe
2. Weijia Xu
3. Gorka Labaka
4. Sebastian Ruder
5. Eneko Agirre
6. Viktor Hangya
7. Zeljko Agic
8. Ndapandula Nakashole
9. Ivan Vulic
10. Jun Shu

Papers from Georgiana Dinu's perspective

Ordered by how strongly the researchers Georgiana Dinu trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Multi-Step Regression Learning for Compositional Distributional Semantics (2013) — 145 citations
• Improving zero-shot learning by mitigating the hubness problem (2014) — 402 citations
• Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors (2014) — 1,522 citations
• Training Neural Machine Translation to Apply Terminology Constraints (2019) — 191 citations
• Improving Gender Translation Accuracy with Filtered Self-Training (2021) — 11 citations
• Toward Mention Detection Robustness with Recurrent Neural Networks (2016) — 38 citations