Jun Suzuki

Artificial Intelligence · with Nagata · 2007–2021

A researcher in the Science corpus: 12 papers; trusts 524 researchers and is trusted by 28 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 190 citations into it; #10,600 of 35,345 by trust here, #12,761 by citations
• Natural Language Processing — 180 citations into it; #1,428 of 5,688 by trust here, #2,263 by citations
• Computer Vision and Pattern Recognition — 72 citations into it; #15,572 of 21,575 by trust here, #16,787 by citations
• Model Architectures — 67 citations into it
• Evaluation & Benchmarks — 24 citations into it
• Optimization & Training — 23 citations into it
• Large Language Models — 17 citations into it
• Representation & Self-Supervised Learning — 11 citations into it; #1,263 of 3,145 by trust here, #2,217 by citations

Whom Jun Suzuki trusts overall

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

1. Ilya Sutskever
2. Yoshua Bengio
3. Geoffrey E. Hinton
4. Oriol Vinyals
5. Diederik P. Kingma
6. Sumit Chopra
7. Alex Krizhevsky
8. Sepp Hochreiter
9. Alexander M. Rush
10. Yann LeCun

Who trusts Jun Suzuki overall

1. Gideon S. Mann
2. Alec Radford
3. Andrew McCallum
4. Sho Takase
5. Dekang Lin
6. Angela Fan
7. Shun Kiyono
8. Joseph P. Turian
9. Mohit Bansal
10. David Grangier

Papers from Jun Suzuki's perspective

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

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

Their papers

• Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization (2016) — 87 citations
• Neural Headline Generation on Abstract Meaning Representation (2016) — 172 citations
• SHAPE: Shifted Absolute Position Embedding for Transformers (2021) — 60 citations
• Direct Output Connection for a High-Rank Language Model (2018) — 37 citations
• Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction (2020) — 163 citations
• Interpretable Adversarial Perturbation in Input Embedding Space for Text (2018) — 208 citations
• An Empirical Study of Building a Strong Baseline for Constituency Parsing (2018) — 16 citations
• Input-to-Output Gate to Improve RNN Language Models (2017) — 6 citations
• RNN-based Encoder-decoder Approach with Word Frequency Estimation (2017) — 13 citations
• Source-side Prediction for Neural Headline Generation (2017) — 9 citations
• Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data (2008) — 154 citations
• Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach (2007) — 40 citations