Jana Straková

Artificial Intelligence · 2014–2017

A researcher in the Science corpus: 3 papers; trusts 33 researchers and is trusted by 24 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 27 citations into it; #7,899 of 35,345 by trust here, #13,760 by citations
• Natural Language Processing — 27 citations into it; #2,127 of 5,688 by trust here, #3,574 by citations
• Model Architectures — 9 citations into it
• Evaluation & Benchmarks — 5 citations into it; #1,339 of 3,147 by trust here, #2,627 by citations

Whom Jana Straková trusts overall

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

1. Michael Collins
2. Christopher D. Manning
3. Diederik P. Kingma
4. Mitchell P. Marcus
5. Geoffrey E. Hinton
6. Alex Graves
7. Chris Dyer
8. Jenny Rose Finkel
9. Sepp Hochreiter
10. Yoshua Bengio

Who trusts Jana Straková overall

1. Ondrej Dusek
2. Milan Straka
3. Franck Burlot
4. Loïc Barrault
5. Philip Williams
6. Mercedes García-Martínez
7. Filip Jurvc'ivcek
8. Lane Schwartz
9. Amanda Cercas Curry
10. François Yvon

Papers from Jana Straková's perspective

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

1. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
2. Attention is All you Need (Neural Information Processing Systems)
3. ImageNet classification with deep convolutional neural networks
4. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
8. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
9. ImageNet: A large-scale hierarchical image database
10. Dropout: a simple way to prevent neural networks from overfitting

Their papers

• UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing (2016) — 472 citations
• Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition (2014) — 185 citations
• Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe (2017) — 628 citations