Sotabase

Career

· AI/ML Researcher (Foundation Models), Apple2025–
· Senior Member of Technical Staff, Essential AI2024–2025
· Consultant, NAVER U.Hub Inc.2022–2024
· Consultant, Bloomberg L.P.2020–2020
· Assistant Professor, Rutgers University2019–2024
· Adjunct Assistant Professor, Columbia University2017–2017
· Research Assistant Professor, Toyota Technological Institute at Chicago2017–2019
· Senior Research Scientist, Bloomberg L.P.2016–2017
· Research Intern, Google Inc.2014–2014
· Research Intern, Microsoft Research2013–2013
· PhD in Computer Science, Columbia University2011–2016
· Research Assistant, Columbia University2011–2016
· Summer Workshop Participant, Johns Hopkins University Center for Language and Speech Processing2011–2011
· Research Intern, University of Rochester2010–2010
· Bachelor of Arts in Mathematics, University of Rochester2008–2011
· Bachelor of Science in Computer Science, University of Rochester2008–2011

Publications (89)

Midge: Generating Image Descriptions From Computer Vision Detections
Conference of the European Chapter of the Association for Computational Linguistics · 2012
490
cited
Formal Limitations on the Measurement of Mutual Information
International Conference on Artificial Intelligence and Statistics · 2018
318
cited
Understanding and predicting importance in images
2012 IEEE Conference on Computer Vision and Pattern Recognition · 2012
162
cited
Frustratingly Easy Neural Domain Adaptation
International Conference on Computational Linguistics · 2016
78
cited
Large Scale Retrieval and Generation of Image Descriptions
International Journal of Computer Vision · 2015
77
cited
Spectral Learning of Latent-Variable PCFGs
Annual Meeting of the Association for Computational Linguistics · 2012
74
cited
ONENET: Joint domain, intent, slot prediction for spoken language understanding
Automatic Speech Recognition & Understanding · 2017
73
cited
Edinburgh Research Explorer Experiments with Spectral Learning of Latent-Variable PCFGs
71
cited
New Transfer Learning Techniques for Disparate Label Sets
Annual Meeting of the Association for Computational Linguistics · 2015
70
cited
Label-Agnostic Sequence Labeling by Copying Nearest Neighbors
Annual Meeting of the Association for Computational Linguistics · 2019
66
cited
Domain Attention with an Ensemble of Experts
Annual Meeting of the Association for Computational Linguistics · 2017
64
cited
EntQA: Entity Linking as Question Answering
International Conference on Learning Representations · 2021
64
cited
Model-based Word Embeddings from Decompositions of Count Matrices
Annual Meeting of the Association for Computational Linguistics · 2015
64
cited
Understanding Hard Negatives in Noise Contrastive Estimation
North American Chapter of the Association for Computational Linguistics · 2021
64
cited
Unsupervised Part-Of-Speech Tagging with Anchor Hidden Markov Models
Transactions of the Association for Computational Linguistics · 2016
63
cited
Adversarial Adaptation of Synthetic or Stale Data
Annual Meeting of the Association for Computational Linguistics · 2017
50
cited
Detecting Visual Text
North American Chapter of the Association for Computational Linguistics · 2012
49
cited
Rethinking Reflection in Pre-Training
arXiv.org · 2025
40
cited
A Spectral Algorithm for Learning Class-Based n-gram Models of Natural Language
Conference on Uncertainty in Artificial Intelligence · 2014
35
cited
Spectral learning of latent-variable PCFGs: algorithms and sample complexity
Journal of machine learning research · 2014
34
cited
Sotabase
Karl Stratos | Researcher Profile | Sotabase | Sotabase