Yoav Artzi
Artificial Intelligence · 2011–2021
A researcher in the Science corpus: 27 papers; trusts 2,475 researchers and is trusted by 3,524 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 917 citations into it; #479 of 36,961 by trust here, #657 by citations
- Natural Language Processing — 588 citations into it; #129 of 5,725 by trust here, #166 by citations
- Computer Vision and Pattern Recognition — 388 citations into it; #1,219 of 21,973 by trust here, #661 by citations
- Evaluation & Benchmarks — 134 citations into it; #218 of 3,155 by trust here, #205 by citations
- Reinforcement Learning — 125 citations into it; #249 of 2,250 by trust here, #321 by citations
- Model Architectures — 111 citations into it; #1,770 of 2,288 by trust here, #1,322 by citations
- Multimodal Learning — 74 citations into it; #384 of 1,215 by trust here, #408 by citations
- Control and Systems Engineering — 53 citations into it
Whom Yoav Artzi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Luke S. Zettlemoyer
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Michael Collins
- Alex Krizhevsky
- Mark Steedman
- Ilya Sutskever
- Kaiming He
- Yann LeCun
Who trusts Yoav Artzi overall
- Percy Liang
- Luke S. Zettlemoyer
- Jayant Krishnamurthy
- Aishwarya Kamath
- Jonathan Berant
- Mohit Bansal
- Siva Reddy
- Dipendra Kumar Misra
- Mirella Lapata
- Tom Kwiatkowski
Papers from Yoav Artzi's perspective
Ordered by how strongly the researchers Yoav Artzi 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
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013) — 485 citations
- BERTScore: Evaluating Text Generation with BERT (2019) — 9,100 citations
- Mapping Instructions and Visual Observations to Actions with Reinforcement Learning (2017) — 256 citations
- Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013) — 334 citations
- A Corpus for Reasoning about Natural Language Grounded in Photographs (2018) — 733 citations
- TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments (2018) — 471 citations
- Learning to Automatically Solve Algebra Word Problems (2014) — 399 citations
- Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction (2018) — 200 citations
- CHALET: Cornell House Agent Learning Environment (2018) — 101 citations
- Bootstrapping Semantic Parsers from Conversations (2011) — 147 citations
- Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020) — 462 citations
- Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies (2018) — 629 citations
- Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight (2019) — 82 citations
- A Corpus of Natural Language for Visual Reasoning (2017) — 277 citations
- Broad-coverage CCG Semantic Parsing with AMR (2015) — 157 citations
- A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution (2021) — 170 citations
- Evaluating NLP Models via Contrast Sets (2020) — 85 citations
- Revisiting Few-sample BERT Fine-tuning (2020) — 505 citations
- Simple Recurrent Units for Highly Parallelizable Recurrence (2017) — 309 citations
- Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following (2020) — 37 citations