Bill Byrne

Artificial Intelligence · 2010–2022

A researcher in the Science corpus: 14 papers; trusts 895 researchers and is trusted by 33 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 282 citations into it; #5,296 of 35,345 by trust here, #5,495 by citations
• Natural Language Processing — 245 citations into it; #1,334 of 5,688 by trust here, #1,667 by citations
• Computer Vision and Pattern Recognition — 129 citations into it; #7,472 of 21,575 by trust here, #9,187 by citations
• Safety, Robustness & Interpretability — 53 citations into it; #749 of 2,251 by trust here, #1,780 by citations
• Model Architectures — 39 citations into it
• Evaluation & Benchmarks — 32 citations into it
• Multimodal Learning — 21 citations into it
• Optimization & Training — 18 citations into it

Whom Bill Byrne trusts overall

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

1. Yoshua Bengio
2. Ilya Sutskever
3. Ashish Vaswani
4. Geoffrey E. Hinton
5. Diederik P. Kingma
6. Rico Sennrich
7. Alex Krizhevsky
8. Kyunghyun Cho
9. Dzmitry Bahdanau
10. Oriol Vinyals

Who trusts Bill Byrne overall

1. Danielle Saunders
2. Felix Stahlberg
3. Andrea Madotto
4. James Thorne
5. Clara Meister
6. Emily Sheng
7. Karolina Stańczak
8. Zhaojiang Lin
9. Erik Ekstedt
10. Rosie Sallis

Papers from Bill Byrne's perspective

Ordered by how strongly the researchers Bill Byrne 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. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset (2019) — 246 citations
• On NMT Search Errors and Model Errors: Cat Got Your Tongue? (2019) — 169 citations
• TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems (2020) — 28 citations
• “Your Word is my Command”: Google Search by Voice: A Case Study (2010) — 253 citations
• Syntactically Guided Neural Machine Translation (2016) — 66 citations
• The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16 (2016) — 7 citations
• Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem (2020) — 158 citations
• The University of Cambridge’s Machine Translation Systems for WMT18 (2018) — 20 citations
• Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It (2020) — 69 citations
• First the Worst: Finding Better Gender Translations During Beam Search (2021) — 38 citations
• Retrieval Augmented Visual Question Answering with Outside Knowledge (2022) — 137 citations
• The practical ethics of bias reduction in machine translation: why domain adaptation is better than data debiasing (2021) — 46 citations
• Domain Adaptive Inference for Neural Machine Translation (2019) — 32 citations
• A Comparison of Neural Models for Word Ordering (2017) — 21 citations