Rafael-Michael Karampatsis

Natural Language Processing · 2019–2020

A researcher in the Science corpus: 2 papers; trusts 120 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Natural Language Processing — 77 citations into it; #5,472 of 5,688 by trust here, #4,250 by citations
• Artificial Intelligence — 75 citations into it; #13,117 of 35,345 by trust here, #17,776 by citations
• Information Systems — 66 citations into it; #2,411 of 8,771 by trust here, #3,402 by citations
• Software — 35 citations into it
• Code Generation & Program Synthesis — 32 citations into it; #82 of 220 by trust here, #183 by citations
• Signal Processing — 21 citations into it
• Program Analysis & Verification — 17 citations into it
• Model Architectures — 14 citations into it; #1,110 of 2,278 by trust here, #2,009 by citations

Whom Rafael-Michael Karampatsis trusts overall

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

1. Miltiadis Allamanis
2. Premkumar T. Devanbu
3. Yoshua Bengio
4. Geoffrey E. Hinton
5. Veselin Raychev
6. Ilya Sutskever
7. Charles Sutton
8. Vincent J. Hellendoorn
9. Kyunghyun Cho
10. Tomas Mikolov

Who trusts Rafael-Michael Karampatsis overall

1. Hlib Babii
2. Matteo Ciniselli
3. Zimin Chen
4. Kevin Jesse
5. Maliheh Izadi
6. Andrea Janes
7. Seohyun Kim
8. Romain Robbes
9. L. Pascarella
10. Yangruibo Ding

Papers from Rafael-Michael Karampatsis's perspective

Ordered by how strongly the researchers Rafael-Michael Karampatsis 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. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
7. Gradient-based learning applied to document recognition
8. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
9. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. ImageNet: A large-scale hierarchical image database

Their papers

• Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code (2020) — 235 citations
• Maybe Deep Neural Networks are the Best Choice for Modeling Source Code (2019) — 56 citations