Kenneth Heafield
Artificial Intelligence · 2011–2024
A researcher in the Science corpus: 22 papers; trusts 880 researchers and is trusted by 3,417 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 371 citations into it; #359 of 36,961 by trust here, #1,311 by citations
- Natural Language Processing — 301 citations into it; #85 of 5,725 by trust here, #334 by citations
- Computer Vision and Pattern Recognition — 93 citations into it; #3,916 of 21,973 by trust here, #3,267 by citations
- Evaluation & Benchmarks — 84 citations into it; #594 of 3,155 by trust here, #1,306 by citations
- Machine Translation — 31 citations into it
- Language and Linguistics — 30 citations into it
- Model Architectures — 30 citations into it
- Optimization & Training — 27 citations into it; #494 of 2,605 by trust here, #1,061 by citations
Whom Kenneth Heafield trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Philipp Koehn
- Rico Sennrich
- Andreas Stolcke
- Yoshua Bengio
- Diederik P. Kingma
- Geoffrey E. Hinton
- Ilya Sutskever
- Kyunghyun Cho
- Dzmitry Bahdanau
- Nadir Durrani
Who trusts Kenneth Heafield overall
- Nadir Durrani
- Ondrej Bojar
- Philipp Koehn
- Felix Stahlberg
- Daniel Quernheim
- Ronan Collobert
- Rajen Chatterjee
- Santanu Pal
- Barry Haddow
- Spence Green
Papers from Kenneth Heafield's perspective
Ordered by how strongly the researchers Kenneth Heafield trusts endorse each paper. Same corpus, a different order for every researcher.
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet classification with deep convolutional neural networks
- 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)
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet: A large-scale hierarchical image database
Their papers
- KenLM: Faster and Smaller Language Model Queries (2011) — 1,599 citations
- Scalable Modified Kneser-Ney Language Model Estimation (2013) — 632 citations
- N-gram Counts and Language Models from the Common Crawl (2014) — 194 citations
- Marian: Fast Neural Machine Translation in C++ (2018) — 797 citations
- The University of Edinburgh’s Neural MT Systems for WMT17 (2017) — 187 citations
- The Llama 3 Herd of Models (2024) — 17,085 citations
- Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014) — 56 citations
- Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering (2018) — 121 citations
- Copied Monolingual Data Improves Low-Resource Neural Machine Translation (2017) — 200 citations
- Edinburgh’s Machine Translation Systems for European Language Pairs (2013) — 43 citations
- ParaCrawl: Web-Scale Acquisition of Parallel Corpora (2020) — 296 citations
- Sparse Communication for Distributed Gradient Descent (2017) — 882 citations
- No Language Left Behind: Scaling Human-Centered Machine Translation (2022) — 1,884 citations
- Findings of the Fourth Workshop on Neural Generation and Translation (2020) — 16 citations
- Gender bias amplification during Speed-Quality optimization in Neural Machine Translation (2021) — 42 citations
- Parallel Sentence Mining by Constrained Decoding (2020) — 23 citations
- Zero-Resource Neural Machine Translation with Monolingual Pivot Data (2019) — 36 citations
- Direct simultaneous speech to speech translation (2021) — 9 citations
- Findings of the 2021 Conference on Machine Translation (WMT21) (2021) — 244 citations
- Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data (2019) — 191 citations