Swabha Swayamdipta
Artificial Intelligence · 2014–2022
A researcher in the Science corpus: 22 papers; trusts 2,082 researchers and is trusted by 576 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,284 citations into it; #1,373 of 36,961 by trust here, #1,155 by citations
- Natural Language Processing — 588 citations into it; #598 of 5,725 by trust here, #434 by citations
- Computer Vision and Pattern Recognition — 473 citations into it; #8,026 of 21,973 by trust here, #4,945 by citations
- Evaluation & Benchmarks — 199 citations into it; #497 of 3,155 by trust here, #316 by citations
- Representation & Self-Supervised Learning — 156 citations into it
- Safety, Robustness & Interpretability — 148 citations into it; #1,322 of 2,259 by trust here, #558 by citations
- Large Language Models — 106 citations into it; #783 of 810 by trust here, #376 by citations
- Optimization & Training — 92 citations into it
Whom Swabha Swayamdipta trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Alex Graves
- Alex Krizhevsky
- Ilya Sutskever
- Kaiming He
- Yann LeCun
- Jimmy Ba
- Richard Socher
Who trusts Swabha Swayamdipta overall
- Mohit Bansal
- Eric Wallace
- Yejin Choi
- Matt Gardner
- Adyasha Maharana
- Kawin Ethayarajh
- Sewon Min
- Yonatan Belinkov
- Noah A. Smith
- Rowan Zellers
Papers from Swabha Swayamdipta's perspective
Ordered by how strongly the researchers Swabha Swayamdipta 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)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Annotation Artifacts in Natural Language Inference Data (2018) — 1,309 citations
- Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (2020) — 3,085 citations
- Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection (2021) — 408 citations
- DyNet: The Dynamic Neural Network Toolkit (2017) — 391 citations
- Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics (2020) — 601 citations
- Adversarial Filters of Dataset Biases (2020) — 248 citations
- DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts (2021) — 533 citations
- WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation (2022) — 265 citations
- Transfer Learning in Natural Language Processing (2019) — 625 citations
- MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers (2021) — 548 citations
- Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016) — 63 citations
- Understanding Dataset Difficulty with V-Usable Information (2021) — 351 citations
- The Right Tool for the Job: Matching Model and Instance Complexities (2020) — 197 citations
- Multi-Mention Learning for Reading Comprehension with Neural Cascades (2017) — 35 citations
- Challenges in Automated Debiasing for Toxic Language Detection (2021) — 162 citations
- Reframing Human-AI Collaboration for Generating Free-Text Explanations (2021) — 176 citations
- G-DAug: Generative Data Augmentation for Commonsense Reasoning (2020) — 92 citations
- Syntactic Scaffolds for Semantic Structures (2018) — 103 citations
- Information-Theoretic Measures of Dataset Difficulty (2021) — 15 citations
- On-the-Fly Controlled Text Generation with Experts and Anti-Experts (2021) — 16 citations