Melvin Johnson
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 25 papers; trusts 1,378 researchers and is trusted by 733 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 962 citations into it; #1,225 of 36,961 by trust here, #359 by citations
- Natural Language Processing — 602 citations into it; #547 of 5,725 by trust here, #97 by citations
- Computer Vision and Pattern Recognition — 340 citations into it; #3,452 of 21,973 by trust here, #425 by citations
- Evaluation & Benchmarks — 162 citations into it; #1,606 of 3,155 by trust here, #903 by citations
- Representation & Self-Supervised Learning — 137 citations into it
- Model Architectures — 105 citations into it
- Large Language Models — 100 citations into it
- Speech & Audio — 97 citations into it
Whom Melvin Johnson trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Alex Krizhevsky
- Alex Graves
- Kyunghyun Cho
- Jimmy Ba
- Yann LeCun
- Oriol Vinyals
Who trusts Melvin Johnson overall
- Ankur Bapna
- Graham Neubig
- Orhan Firat
- Yulia Tsvetkov
- Carlos Escolano
- Naveen Arivazhagan
- Holger Schwenk
- Guillaume Lample
- Yonatan Belinkov
- Prithviraj Ammanabrolu
Papers from Melvin Johnson's perspective
Ordered by how strongly the researchers Melvin Johnson trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016) — 7,325 citations
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation (2016) — 2,235 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation (2018) — 479 citations
- Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019) — 477 citations
- XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization (2020) — 1,171 citations
- Massively Multilingual Neural Machine Translation (2019) — 549 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation (2018) — 172 citations
- Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation (2019) — 76 citations
- Leveraging Linguistic Structure For Open Domain Information Extraction (2015) — 821 citations
- XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation (2021) — 234 citations
- mSLAM: Massively multilingual joint pre-training for speech and text (2022) — 133 citations
- Rethinking embedding coupling in pre-trained language models (2020) — 187 citations
- Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation (2018) — 65 citations
- The Missing Ingredient in Zero-Shot Neural Machine Translation (2019) — 123 citations
- SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training (2021) — 102 citations
- They, Them, Theirs: Rewriting with Gender-Neutral English (2021) — 66 citations
- Direct speech-to-speech translation with a sequence-to-sequence model (2019) — 281 citations
- Small and Practical BERT Models for Sequence Labeling (2019) — 128 citations