Slav Petrov
Artificial Intelligence · 2006–2023
A researcher in the Science corpus: 28 papers; trusts 623 researchers and is trusted by 2,607 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 738 citations into it; #497 of 36,961 by trust here, #321 by citations
- Natural Language Processing — 428 citations into it; #236 of 5,725 by trust here, #301 by citations
- Computer Vision and Pattern Recognition — 163 citations into it; #2,489 of 21,973 by trust here, #425 by citations
- Evaluation & Benchmarks — 159 citations into it; #633 of 3,155 by trust here, #157 by citations
- Model Architectures — 45 citations into it
- Information Systems — 44 citations into it; #1,130 of 9,233 by trust here, #3,943 by citations
- Language and Linguistics — 40 citations into it; #130 of 3,482 by trust here, #114 by citations
- Representation & Self-Supervised Learning — 29 citations into it
Whom Slav Petrov trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Eugene Charniak
- Daniel Klein
- Michael Collins
- Liang Huang
- Christopher D. Manning
- Thorsten Brants
- Geoffrey E. Hinton
- Takuya Matsuzaki
- Sabine Buchholz
- Max Welling Donald
Who trusts Slav Petrov overall
- Yoav Goldberg
- Daniel Klein
- Trevor Cohn
- Sebastian Ruder
- Richard Socher
- Percy Liang
- Zhongqiang Huang
- Greg Durrett
- Ivan Titov
- James Henderson
Papers from Slav Petrov's perspective
Ordered by how strongly the researchers Slav Petrov trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- 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
- 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)
- 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)
Their papers
- PaLM: Scaling Language Modeling with Pathways (2022) — 8,214 citations
- Natural Questions: A Benchmark for Question Answering Research (2019) — 4,925 citations
- Grammar as a Foreign Language (2014) — 942 citations
- Scaling Instruction-Finetuned Language Models (2022) — 4,301 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- Learning Accurate, Compact, and Interpretable Tree Annotation (2006) — 991 citations
- Globally Normalized Transition-Based Neural Networks (2016) — 577 citations
- Universal Dependencies v1: A Multilingual Treebank Collection (2016) — 1,486 citations
- Improved Inference for Unlexicalized Parsing (2007) — 722 citations
- Overview of the 2012 Shared Task on Parsing the Web (2012) — 188 citations
- Transcending Scaling Laws with 0.1% Extra Compute (2022) — 78 citations
- Structured Training for Neural Network Transition-Based Parsing (2015) — 236 citations
- Measuring Attribution in Natural Language Generation Models (2021) — 277 citations
- A Universal Part-of-Speech Tagset (2011) — 1,071 citations
- Universal Dependency Annotation for Multilingual Parsing (2013) — 603 citations
- Dependency Parsing (2009) — 624 citations
- Universal Dependencies 2.1 (2017) — 425 citations
- Syntactic Annotations for the Google Books NGram Corpus (2012) — 473 citations
- Temporal Analysis of Language through Neural Language Models (2014) — 363 citations
- CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2018) — 433 citations