Hello! I'm a fifth and final year graduate student in the Computer Science Department at UMass Amherst, and via cotutelle at Macquarie University, where I work in natural language processing and machine learning. My advisors are David Smith and Mark Johnson. I'm also occasionally in South College, pretending to be a linguist.
My Erdős–Bacon number is arguably no greater than 8.
My research focuses on statistical models of natural language processing and acquisition, with an emphasis on joint inference, unsupervised learning and statistical relational learning. In my dissertation I present efficient methods for representing syntax in graphical models, and techniques for leveraging these representations to improve performance on related NLP problems. In particular, I develop methods for training such models in the absence of syntactic annotation, learning latent syntactic representations that best support the desired end task. My old research statement is still relevant, but not pursued in my dissertation.
Combinatorial Constraints for Constituency Parsing in Graphical Models
Jason Naradowsky, David Smith
Technical Report, University of Massachusetts Amherst, 2012.
Natural Language Toolkit (NLTK):
The Natural Language Toolkit is a collection of open source Python modules that can be used freely for research or pedagogical purposes. There's also a book out now documenting how to use the NTLK - it doubles as an introductory computational linguistics coursebook. For the summer of 2008 I worked on the NLTK while sponsored under the Google Summer of Code program, during which time I implemented a suite of dependency parsers under the supervision of Sebastian Riedel and Jason Baldridge.