Michael Wick
Principal Member Technical Staff
Michael Wick
Michael Wick joined Oracle Labs Burlington in 2014. He completed his Ph.D. in Computer Science under adviser Andrew McCallum at the University of Massachusetts, Amherst. His interest in developing new machine learning and inference algorithms is driven by applications such as information extraction, data integration, and knowledge base construction. In 2009 he received the Yahoo! Award for Excellence in Search and Mining and in 2010 he received the Yahoo! Key Scientific Challenges award. He is also an organizer of the 2012 and 2013 ICML workshops Inferning: Interactions Between Inference and Learning. He is a former TA for Graphical Models (CMPSCI 691), and a former organizer for the Machine Learning and Friends lunch.
My UMass research page.
An approximation of my publications on Google scholar.
Inferning 2013 proceedings.
Publications
In Proceedings
Online Post-Processing in Rankings for Fair Utility Maximization
Gupta, Ananya*, Johnson, Eric*, Payan, Justin, Roy, Aditya Kumar, Kobren, Ari, Panda, Swetasudha, Tristan, Jean-Baptiste, Michael Wick
In Proceedings
Verification of ML Systems via Reparameterization.
Jean-Baptiste Tristan, Joseph Tassarotti, Koundinya Vajjha, Michael L. Wick, Anindya Banerjee 0001
In Proceedings
Detecting and Exorcising Statistical Demons from Language Models with Anti-Models of Negative Data.
Michael L. Wick, Kate Silverstein, Jean-Baptiste Tristan, Adam Craig Pocock, Mark Johnson
In Proceedings
“Using Bayes Factors to Control for Fairness A Case Study on Learning to Rank”
Tristan, J.-B., Mahmoudian H, Swetasudha Panda, Pallika Kanani, Michael Wick
In Proceedings
Scaling Hierarchical Coreference with Homomorphic Compression.
Michael Wick, Swetasudha Panda, Joseph Tassarotti, Jean-Baptiste Tristan
In Proceedings
Unlocking Fairness - a Trade-off Revisited.
Michael Wick, Swetasudha Panda, Jean-Baptiste Tristan
In Proceedings
Gradient-Based Inference for Networks with Output Constraints.
Jay Yoon Lee, Sanket Vaibhav Mehta, Michael Wick, Jean-Baptiste Tristan, Jaime G. Carbonell
In Proceedings
Sketching for Latent Dirichlet-Categorical Models.
Joseph Tassarotti, Jean-Baptiste Tristan, Michael Wick
In Proceedings
Sketching for Latent Dirichlet-Categorical Models.
Joseph Tassarotti, Jean-Baptiste Tristan, Michael Wick
In Proceedings
Enforcing Output Constraints via SGD - A Step Towards Neural Lagrangian Relaxation.
Jay Yoon Lee, Michael Wick, Jean-Baptiste Tristan, Jaime G. Carbonell
In Proceedings
Exponential Stochastic Cellular Automata for Massively Parallel Inference
Manzil Zaheer, Michael Wick, Jean-Baptiste Tristan, Alex Smola, Guy Steele
In Proceedings
Minimally Constrained Multilingual Word Embeddings via Artificial Code Switching
Michael Wick, Pallika Kanani, Adam Pocock
Misc
Attribute Extraction from Noisy Text Using Character-based Sequence Tagging Models
Pallika Kanani, Michael Wick, Adam Pocock
Misc
Minimally Constrained Multilingual Word Embeddings via Artificial Code Switching
Michael Wick, Pallika Kanani, Adam Pocock
In Proceedings
A Joint Model for Discovering and Linking Entities
Michael Wick, Sameer Singh, Harshal Pandya, Andrew McCallum
In Proceedings
Assessing Confidence of Knowledge Base Content with an Experimental Study in Entity Resolution
Michael Wick, Sameer Singh, Ari Kobren, Andrew McCallum
In Proceedings
Probabilistic Reasoning about Human Edits in Information Integration.
Michael Wick, Ari Kobren, Andrew McCallum
In Proceedings
Large-scale author coreference via hierarchical entity representations.
Michael Wick, Ari Kobren, Andrew McCallum
In Proceedings
Assessing confidence of knowledge base content with an experimental study in entity resolution.
Michael L. Wick, Sameer Singh 0001, Ari Kobren, Andrew McCallum
In Proceedings
MCMCMC: Efficient Inference by Approximate Sampling
Sameer Singh, Michael Wick, Andrew McCallum
In Proceedings
A Discriminative Hierarchical Model for Fast Coreference at Large Scale
Michael Wick, Sameer Singh, Andrew McCallum
In Proceedings
Human Machine Cooperation with Epistemological DBs: Supporting User Corrections to Automatically Constructed KBs
Michael Wick, Karl Schultz, Andrew McCallum
In Proceedings
Monte Carlo MCMC: Efficient Inference by Sampling Factors
Sameer Singh, Michael Wick, Andrew McCallum
In Proceedings
SampleRank: Training Factor Graphs with Atomic Gradients
Michael Wick, Khashayar Rohanimanesh, Kedare Bellare, Aron Culotta, Andrew McCallum
In Proceedings
Hybrid In-Database Inference for Declarative Information Extraction
Daisy Zhe Wang, Michael J. Franklin, Minos Garofalakis, Joseph M. Hellerstein, Michael Wick
Technical Report
Distantly labeling data for large scale cross-document coreference
Sameer Singh, Michael Wick, Andrew McCallum
In Proceedings
Scalable Probabilistic Databases with Factor Graphs and MCMC
Michael Wick, Andrew McCallum, Gerome Miklau
In Proceedings
Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference
Michael Wick, Khashayar Rohanimanesh, Sameer Singh, Andrew McCallum
In Proceedings
SampleRank: Learning Preferences from Atomic Gradients
Michael Wick, Khashayar Rohanimanesh, Aron Culotta, Andrew McCallum
Annual Report
An Entity Based Model for Coreference Resolution
Michael Wick, Aron Culotta, Khashayar Rohanimanesh, Andrew McCallum
Technical Report
Advances in Learning and Inference for Partition-wise Models of Coreference Resolution
Michael Wick, Andrew McCallum
Technical Report
Inference and Learning in Large Factor Graphs with Adaptive Proposal Distributions
Khashayar Rohanimanesh, Michael Wick, Andrew McCallum
Annual Report
A Corpus for Cross-Document Co-reference
David Day, Janet Hitzeman, Michael Wick, Keith Crouch, Massimo Poesio
Technical Report
Reinforcement Learning for MAP Inference in Large Factor Graphs
Khashayar Rohanimanesh, Michael Wick, Sameer Singh, Andrew McCallum
In Proceedings
FACTORIE: Efficient Probabilistic Programming for Relational Factor Graphs via Imperative Declarations of Structure, Inference and Learning
Andrew McCallum, Khashayar Rohanimanesh, Michael Wick, Karl Schultz, Sameer Singh
In Proceedings
A Unified Approach for Schema Matching, Coreference,and Canonicalization
Michael Wick, Khashayar Rohanimanesh, Karl Schultz, Andrew McCallum
In Proceedings
A Discriminative Approach to Ontology Alignmen
Michael Wick, Khashayar Rohanimanesh, Andrew McCallum, AnHai Doan
Technical Report
Exploiting Encyclypedic and Lexical Resources for Entity Disambiguation
Massimo Poesio, David Day, Ron Arstein, Jason Dunacn, Vladimir Eidelman, Claudio Guiliano, Rob Hall, Janet Hitzeman, Alan Jern, Mijail Kabadjov, Gideon Mann, Paul McNamee, Alessandro Moschitti, Simone Ponzetto, Jason Smith, Josef Steinberger, Michael Strube, Jian Su, Yannick Versley, Xiaofeng Yang, Michael Wick, Michael Wick
In Proceedings
Canonicalization of Database Records using Adaptive Similarity Measures
Aron Culotta, Michael Wick, Rob Hall, Matthew Marzilli, Andrew McCallum
In Proceedings
Author Disambiguation using Error-Driven Machine Learning With a Ranking Loss Function
Aron Culotta, Pallika Kanani, Robert Hall, Michael Wick, Andrew McCallum
In Proceedings
Context-Sensitive Error Correction: Using Topic Models to Improve OCR
Michael Wick, Michael Ross, Erik Learned-Miller
In Proceedings
First Order Probabilistic Models for Coreference Resolution
Aron Culotta, Michael Wick, Rob Hall, Andrew McCallum
In Proceedings
Learning Field Compatibilities to Extract Database Records from Unstructured Text
Michael Wick, Aron Culotta, Andrew McCallum