Taylor Berg-Kirkpatrick
Artificial Intelligence · with Neubig · 2017–2023
A researcher in the Science corpus: 14 papers; trusts 1,675 researchers and is trusted by 101 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 431 citations into it; #3,681 of 36,961 by trust here, #4,150 by citations
- Natural Language Processing — 248 citations into it; #1,308 of 5,725 by trust here, #1,498 by citations
- Computer Vision and Pattern Recognition — 170 citations into it; #5,317 of 21,973 by trust here, #3,622 by citations
- Large Language Models — 66 citations into it; #473 of 810 by trust here, #715 by citations
- Representation & Self-Supervised Learning — 65 citations into it
- Evaluation & Benchmarks — 57 citations into it; #2,247 of 3,155 by trust here, #2,911 by citations
- Generative Models — 57 citations into it; #598 of 1,963 by trust here, #687 by citations
- Model Architectures — 45 citations into it
Whom Taylor Berg-Kirkpatrick trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Kaiming He
- Yann LeCun
- Jimmy Ba
- Alex Graves
- Sepp Hochreiter
Who trusts Taylor Berg-Kirkpatrick overall
- John Wieting
- Kalpesh Krishna
- Yixin Liu
- Sachin Kumar
- Graham Neubig
- Bryan Eikema
- Peng Xu
- Chunyuan Li
- Dinghan Shen
- Tianxiao Shen
Papers from Taylor Berg-Kirkpatrick's perspective
Ordered by how strongly the researchers Taylor Berg-Kirkpatrick 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
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- 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)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Improved Variational Autoencoders for Text Modeling using Dilated Convolutions (2017) — 403 citations
- Towards a Unified View of Parameter-Efficient Transfer Learning (2021) — 1,223 citations
- Unsupervised Text Style Transfer using Language Models as Discriminators (2018) — 278 citations
- Lagging Inference Networks and Posterior Collapse in Variational Autoencoders (2019) — 307 citations
- Beyond BLEU:Training Neural Machine Translation with Semantic Similarity (2019) — 188 citations
- Efficient Nearest Neighbor Language Models (2021) — 124 citations
- Simple and Effective Paraphrastic Similarity from Parallel Translations (2019) — 52 citations
- Prompt Consistency for Zero-Shot Task Generalization (2022) — 97 citations
- Differentiable Scheduled Sampling for Credit Assignment (2017) — 40 citations
- Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels (2021) — 55 citations
- A Bilingual Generative Transformer for Semantic Sentence Embedding (2019) — 34 citations
- Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis-Hastings (2021) — 54 citations
- Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models (2022) — 91 citations
- Membership Inference Attacks against Language Models via Neighbourhood Comparison (2023) — 339 citations