David McClosky

I'm currently at Google NYC. Previously, I was a research scientist at IBM Research. Before that, I was a postdoc at Stanford NLP working with Chris Manning and Dan Jurafsky. Going further back, I was a doctoral student working with Eugene Charniak and Mark Johnson in BLLIP at Brown CS. In 2007, I was a visiting student at ÚFAL at Charles Univeristy in Prague. I'm interested in statistical natural language processing, specifically semi-supervised and unsupervised methods (e.g., self-training), domain adaptation, parsing, morphology and information extraction.

CV | Google Scholar | Code | @dmcclosky | ude.drofnats.sc@ccmd

• July 2016: Talk at Text IQ.
• June 2016: Oren Melamud, Mohit Bansal, and Siddharth Patwardhan have a paper on word embeddings at NAACL 2016.
• Feburary 2016: I joined Google NYC.
• November 16, 2015: Talk at Columbia University.
• September 24, 2015: Talk at IBM Research - Ireland.
• September 23, 2015: Talk at DCU.
• September 2015: Attending EMNLP 2015 in Lisbon, Portugal.
• September 2015: DK Choe, Eugene Charniak and I have a paper on syntactic parse fusion at EMNLP 2015. Code is available as part of BLLIP Parser.
• July 2015: New Python version of bllipparser supports parsing constraints and other API improvements. PyPI page.
• June 2015: Attending NAACL 2015 in Denver.
• June 2015: Happy to be working with Oren Melamud for his IBM internship.
• June 2015: There is now an extended version ("director's cut") of the paraphrase parsing paper with additional analysis and examples from the paraphrase dataset.
• April 2015: DK Choe and I have a paper on how to parse paraphrases at ACL 2015.

(older news)