Shankar Kumar
Artificial Intelligence · 2001–2020
A researcher in the Science corpus: 11 papers; trusts 472 researchers and is trusted by 161 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 178 citations into it; #2,707 of 36,961 by trust here, #4,476 by citations
- Natural Language Processing — 104 citations into it; #737 of 5,725 by trust here, #1,147 by citations
- Computer Vision and Pattern Recognition — 39 citations into it; #14,293 of 21,973 by trust here, #11,192 by citations
- Model Architectures — 37 citations into it
- Signal Processing — 34 citations into it
- Speech & Audio — 29 citations into it
- Large Language Models — 12 citations into it
- Optimization & Training — 12 citations into it
Whom Shankar Kumar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Michael Collins
- Franz Joseph Och
- Alex Graves
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Vaibhava Goel
- Oriol Vinyals
- Kaiming He
- Diederik P. Kingma
Who trusts Shankar Kumar overall
- Philipp Koehn
- Felix Stahlberg
- Franz Joseph Och
- Nadir Durrani
- Jiwei Li
- Phil Blunsom
- Barry Haddow
- Alex Kulesza
- Khanh Nguyen
- Kevin Gimpel
Papers from Shankar Kumar's perspective
Ordered by how strongly the researchers Shankar Kumar 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
- Long Short-Term Memory
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- 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)
- ImageNet: A large-scale hierarchical image database
- 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)
Their papers
- Minimum Bayes-Risk Decoding for Statistical Machine Translation (2004) — 518 citations
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
- A Smorgasbord of Features for Statistical Machine Translation (2004) — 325 citations
- Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss (2020) — 539 citations
- Normalization of non-standard words (2001) — 397 citations
- Video suggestion and discovery for youtube: taking random walks through the view graph (2008) — 521 citations
- Lattice rescoring strategies for long short term memory language models in speech recognition (2017) — 41 citations
- Corpora Generation for Grammatical Error Correction (2019) — 146 citations
- Seq2Edits: Sequence Transduction Using Span-level Edit Operations (2020) — 102 citations
- Minimum Bayes-Risk Word Alignments of Bilingual Texts (2002) — 74 citations
- No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models (2017) — 54 citations