I'm a PhD candidate at UMass Amherst working in the Information Extraction and Synthesis Laboratory (IESL) with Professor Andrew McCallum. My thesis work is on automatic knowledge base construction with Universal Schemas.
Previously at UMass, I recieved my M.S. in Computer Science in Fall 2014 as well as my B.S. in Neuroscience and B.A. in Computer Science in May 2012.
In summer 2013 I was a Software Engineering Intern at TripAdvisor.
In summer 2016 I was an intern at Google Research working with the Commonsense team on multilingual commonsense knowledge base construction.
- Fast and Accurate Sequence Labeling with Iterated Dilated Convolutions Emma Strubell, Patrick Verga , David Belanger and Andrew McCallum. Arxiv Preprint
- Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema Patrick Verga , Arvind Neelakantan and Andrew McCallum. EACL, 2017 (oral presentation) [code] [data]
- Multilingual Relation Extraction using Compositional Universal Schema. Patrick Verga , David Belanger, Emma Strubell, Benjamin Roth, and Andrew McCallum. NAACL, 2016 (oral presentation) [code] [data]
- Row-less Universal Schema Patrick Verga and Andrew McCallum AKBC 2016 (oral presentation)
- Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema Haw-Shiuan Chang, Abdurrahman Munir, Ao Liu, Johnny Tian-Zheng Wei, Aaron Traylor, Ajay Nagesh, Nicholas Monath, Patrick Verga, Emma Strubell and Andrew McCallum TAC KBP 2016 Workshop
- Building Knowledge Bases with Universal Schema: Cold Start and Slot-Filling Approaches Bejamin Roth, Nicholas Monath, David Belanger, Emma Strubell, Patrick Verga and Andrew McCallum TAC KBP 2015 Workshop
- Emotional trait and memory associates of sleep timing and quality. EF Pace-Schott, ZS Rubin, LE Tracy, RMC Spencer, SP Orr, and Patrick Verga Psychiatry Research, 2015
- UMass at TREC WEB 2014: Entity Query Feature Expansion using Knowledge Base Links. Laura Dietz and Patrick Verga In Proceedings of the TREC 2014 Conference, 2014
- Efficient Unsupervised Authorship Clustering Using Impostor Similarity. Patrick Verga, James Allan, Brian Levine, Marc Liberatore. Tech Report 2014. [code]
- Modeling Reconsolidation in Kernel Associative Memory Dimitri Nowicki, Patrick Verga, Hava Siegelmann. PloS one 8 (8), e68189. 2013
- Extinction of conditioned fear is better learned and recalled in the morning than in the evening. Edward F Pace-Schott, Rebecca Spencer, Shilpa Vijayakumar, Nafis AK Ahmed, Patrick W Verga, Scott P Orr, Roger K Pitman, Mohammed R Milad. Journal of psychiatric research 47 (11), 1776-1784 2013
- Sleep promotes consolidation and generalization of extinction learning in simulated exposure therapy for spider fear Edward F Pace-Schott, Patrick W Verga, Tobias S Bennett, Rebecca Spencer. Journal of psychiatric research 46 (8), 1036-1044 2012.
- Smart Plant / Sentiment Analysis Arduino-based "smart" plant companion monitors moisture and sends alerts when thirsty. Built Twitter sentiment analysis model (Python, NumPy, scikit-learn) to re-tweet negative tweets when thirsty, and positive ones after being watered.
- Android app Designed and implemented an android app with Emma Strubell to access the online game NationStates. It is the most widely used app for the game with over 10,000 downloads.
Other Things About Pat
I enjoy playing music. I play both bass and mandolin.
I also like hiking and camping.
I have a free range bearded dragon named Bran.
Amherst, Massachusetts, USA
pat (at) cs (dot) umass (dot) edu