Mohit Iyyer
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 32 papers; trusts 2,443 researchers and is trusted by 3,241 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,091 citations into it; #398 of 36,961 by trust here, #318 by citations
- Natural Language Processing — 737 citations into it; #122 of 5,725 by trust here, #70 by citations
- Computer Vision and Pattern Recognition — 350 citations into it; #3,728 of 21,973 by trust here, #1,528 by citations
- Evaluation & Benchmarks — 185 citations into it; #1,435 of 3,155 by trust here, #2,375 by citations
- Large Language Models — 124 citations into it
- Representation & Self-Supervised Learning — 108 citations into it; #212 of 3,156 by trust here, #51 by citations
- Model Architectures — 93 citations into it
- Information Systems — 74 citations into it
Whom Mohit Iyyer trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard Socher
- Diederik P. Kingma
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Tomas Mikolov
- Alex Krizhevsky
- Yann LeCun
- Christopher D. Manning
- Sepp Hochreiter
Who trusts Mohit Iyyer overall
- Yoav Goldberg
- Eric Wallace
- John Wieting
- Mohit Bansal
- Yonatan Belinkov
- Percy Liang
- Caiming Xiong
- Jianfeng Gao
- Jordan L. Boyd-Graber
- Zhe Gan
Papers from Mohit Iyyer's perspective
Ordered by how strongly the researchers Mohit Iyyer 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
- ImageNet: A large-scale hierarchical image database
- 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)
- 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)
Their papers
- Deep Contextualized Word Representations (2018) — 12,212 citations
- Ask Me Anything: Dynamic Memory Networks for Natural Language Processing (2015) — 1,220 citations
- QuAC: Question Answering in Context (2018) — 904 citations
- Deep Unordered Composition Rivals Syntactic Methods for Text Classification (2015) — 842 citations
- A Neural Network for Factoid Question Answering over Paragraphs (2014) — 375 citations
- Search-based Neural Structured Learning for Sequential Question Answering (2017) — 278 citations
- Adversarial Example Generation with Syntactically Controlled Paraphrase Networks (2018) — 786 citations
- Exploring and Predicting Transferability across NLP Tasks (2020) — 190 citations
- Pathologies of Neural Models Make Interpretations Difficult (2018) — 343 citations
- Hurdles to Progress in Long-form Question Answering (2021) — 237 citations
- Reformulating Unsupervised Style Transfer as Paraphrase Generation (2020) — 281 citations
- Do Long-Range Language Models Actually Use Long-Range Context? (2021) — 107 citations
- Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships (2016) — 152 citations
- The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation (2021) — 136 citations
- Political Ideology Detection Using Recursive Neural Networks (2014) — 329 citations
- Thieves on Sesame Street! Model Extraction of BERT-based APIs (2019) — 261 citations
- Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders (2019) — 129 citations
- STraTA: Self-Training with Task Augmentation for Better Few-shot Learning (2021) — 66 citations
- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation (2023) — 1,471 citations
- Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models (2020) — 67 citations