Sotabase

Career

· Staff Research Scientist, Zoom2024–
· Co-Founder, Trove AI2023–2024
· Tech Lead - Machine Learning, Cresta2021–2023
· Senior Researcher, Microsoft2020–2021
· Research Intern, Google2019–2019
· Research Intern, Microsoft2018–2018

Publications (48)

What Makes Good In-Context Examples for GPT-3?
Workshop on Knowledge Extraction and Integration for Deep Learning Architectures; Deep Learning Inside Out · 2021
1,638
cited
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Computer Vision and Pattern Recognition · 2018
602
cited
Joint Embedding of Words and Labels for Text Classification
Annual Meeting of the Association for Computational Linguistics · 2018
417
cited
Adversarial Feature Matching for Text Generation
International Conference on Machine Learning · 2017
351
cited
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Annual Meeting of the Association for Computational Linguistics · 2018
342
cited
Video Generation From Text
AAAI Conference on Artificial Intelligence · 2017
298
cited
Representation Learning
Graph Neural Networks: Foundations, Frontiers, and Applications · 2022
190
cited
A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation
arXiv.org · 2020
145
cited
Topic-Guided Variational Auto-Encoder for Text Generation
North American Chapter of the Association for Computational Linguistics · 2019
131
cited
Adversarial Text Generation via Feature-Mover's Distance
Neural Information Processing Systems · 2018
129
cited
Understanding the solvent-assisted crystallization mechanism inherent in efficient organic–inorganic halide perovskite solar cells
2014
129
cited
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Annual Meeting of the Association for Computational Linguistics · 2020
104
cited
Improving Sequence-to-Sequence Learning via Optimal Transport
International Conference on Learning Representations · 2019
96
cited
MixKD: Towards Efficient Distillation of Large-scale Language Models
International Conference on Learning Representations · 2020
88
cited
Topic Compositional Neural Language Model
International Conference on Artificial Intelligence and Statistics · 2017
84
cited
CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
International Conference on Learning Representations · 2020
77
cited
Deconvolutional Latent-Variable Model for Text Sequence Matching
AAAI Conference on Artificial Intelligence · 2017
69
cited
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
Annual Meeting of the Association for Computational Linguistics · 2018
62
cited
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
Annual Meeting of the Association for Computational Linguistics · 2019
55
cited
Syntax-Infused Variational Autoencoder for Text Generation
Annual Meeting of the Association for Computational Linguistics · 2019
52
cited
Sotabase
Dinghan Shen | Researcher Profile | Sotabase | Sotabase