Sumithra Bhakthavatsalam

Artificial Intelligence · 2019–2021

A researcher in the Science corpus: 3 papers; trusts 13 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 62 citations into it; #23,068 of 35,345 by trust here, #17,110 by citations
• Natural Language Processing — 53 citations into it; #3,881 of 5,688 by trust here, #3,478 by citations
• Evaluation & Benchmarks — 28 citations into it; #2,058 of 3,147 by trust here, #2,095 by citations
• Molecular Biology — 5 citations into it; #9,421 of 17,773 by trust here, #14,833 by citations

Whom Sumithra Bhakthavatsalam trusts overall

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

1. Peter Clark
2. Tushar Khot
3. Oren Etzioni
4. Daniel Khashabi
5. Ashish Sabharwal
6. Ronald J. Williams
7. Todor Mihaylov
8. Robyn Speer
9. Geoffrey E. Hinton
10. Chin-Yew Lin

Who trusts Sumithra Bhakthavatsalam overall

1. Bill Yuchen Lin
2. Xiang Ren
3. Woojeong Jin
4. Ninareh Mehrabi
5. Hanjie Chen
6. Nora Kassner
7. Chenguang Zhu
8. Seyeon Lee
9. Dong-Ho Lee
10. Jay Pujara

Papers from Sumithra Bhakthavatsalam's perspective

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

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

Their papers

• From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project (2019) — 106 citations
• Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge (2021) — 99 citations
• GenericsKB: A Knowledge Base of Generic Statements (2020) — 77 citations