Gregory Druck
LinkedIn

I am the Chief AI Officer at Graphite, where my team builds topic graphs, AI-powered writing tools, and feedback loops to maximize the ROI of organic content. Previously, I was Chief Data Scientist at Yummly, where I led the development of machine learning algorithms for extracting, structuring, searching, and recommending food-related content, and analyzed behavioral data to understand the food world. Before that, I was a Postdoctoral Scientist at Yahoo! Research. In 2011, I received a Ph.D. in Computer Science from the University of Massachusetts Amherst. I was advised by Andrew McCallum. In 2005, I received a B.S. in Computer Science from Johns Hopkins University.

Resume
Publications
Recipe Attribute Prediction using Review Text as Supervision
Gregory Druck
In Proceedings of the IJCAI Workshop on Cooking with Computers, 2013.
[abstract] [bib] [pdf]
Spice it up? Mining Refinements to Online Instructions from User Generated Content
Gregory Druck and Bo Pang
Proceedings of ACL 2012
[abstract] [bib] [pdf]
Generalized Expectation Criteria for Lightly Supervised Learning
Gregory Druck
Ph.D. Thesis, 2011
[bib] [pdf] [note]
Toward Interactive Training and Evaluation
Gregory Druck, Andrew McCallum.
In Proceedings of CIKM 2011
[abstract] [bib] [pdf]
TUTORIAL: Rich Prior Knowledge in Learning for Natural Language Processing
Gregory Druck, Kuzman Ganchev, João Graça.
Presented at ACL 2011, Interspeech 2011
[abstract]
High-Performance Semi-Supervised Learning using Discriminatively Constrained Generative Models
Gregory Druck, Andrew McCallum.
In Proceedings of ICML 2010
[abstract] [bib] [pdf]
Computing Conditional Feature Covariance in Non-Projective Tree Conditional Random Fields
Gregory Druck, David Smith.
University of Massachusetts Technical Report # UM-CS-2009-060.
[abstract] [bib] [pdf]
Active Learning by Labeling Features
Gregory Druck, Burr Settles, Andrew McCallum.
In Proceedings of EMNLP 2009.
[abstract] [bib] [pdf]
Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria.
Gregory Druck, Gideon Mann, Andrew McCallum.
In Proceedings of ACL 2009.
This technical report describes a more effecient training algorithm.
[abstract] [bib] [pdf]
Alternating Projections for Learning with Expectation Constraints.
Kedar Bellare, Gregory Druck, Andrew McCallum.
In Proceedings of UAI 2009.
[abstract] [bib] [pdf]
Learning from Labeled Features using Generalized Expectation Criteria.
Gregory Druck, Gideon Mann, Andrew McCallum.
In Proceedings of SIGIR 2008.
A version of this paper appeared in the Proceedings of NESCAI 2008.
A version of this paper appeared as U. of Massachusetts Amherst Tech. Report UM-CS-2007-62.
An implementation of this method is now part of MALLET. See the tutorial.
[abstract] [bib] [pdf]
Learning to Predict the Quality of Contributions to Wikipedia.
Gregory Druck, Gerome Miklau, Andrew McCallum.
In Proceedings of the AAAI Workshop on Wikipedia and AI, 2008.
[abstract] [bib] [pdf]
Leveraging Existing Resources using Generalized Expectation Criteria.
Gregory Druck, Gideon Mann, Andrew McCallum.
In NIPS Workshop on Learning Problem Design, 2007
Updated: 12/17/07
[abstract] [bib] [pdf]
Generalized Expectation Criteria.
Andrew McCallum, Gideon Mann, Gregory Druck.
U. of Massachusetts Amherst Tech. Report UM-CS-2007-60
This working note has not been updated recently. The 2008 SIGIR, and 2009 ACL and EMNLP papers provide up-to-date descriptions of GE.
[abstract] [bib] [pdf]
Semi-Supervised Classification with Hybrid Generative/Discriminative Methods.
Gregory Druck, Chris Pal, Xiaojin Zhu, Andrew McCallum.
In Proceedings of KDD 2007.
[abstract] [bib] [pdf]
Learning A* Underestimates: Using Inference to Guide Inference.
Gregory Druck, Mukund Narasimhan, Paul Viola.
In Proceedings of AISTATS 2007
[abstract] [bib] [pdf]
Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification.
Andrew McCallum, Chris Pal, Gregory Druck, Xuerui Wang.
In Proceedings of AAAI 2006.
[abstract] [bib] [pdf]