I am a research scientist at Google in New York. I work on natural language processing. Primarily,
I focus on modeling unannotated information to learn better statistical models for the analysis of
natural language syntax and semantics.
Before joining Google, I finished a Ph.D. at the Language Technologies Institute of the
School of Computer Science at Carnegie Mellon University. My Ph.D. advisor was Noah Smith,
and I was a member of Noah’s ARK.
I finished a Masters degree at CMU in 2008 under the supervision of Alexander I. Rudnicky.
Before coming to CMU, I completed an undergraduate degree in Computer Science and
Engineering at the Indian Institute of Technology, Kharagpur.
News:
- An article on weakly-supervised part-of-speech tagging has been accepted for publication at the Transactions of the Association for Computational Linguistics.
- An article on frame-semantic parsing has been accepted for publication at the Computational Linguistics Journal.
- I joined Google, New York as a research scientist in June, 2012.
- I successfully defended my Ph.D. thesis titled "Semi-Supervised and Latent-Variable Models of Natural Language Semantics" on April 23, 2012. The thesis is available here, and the defense slides are available here.
- Our paper on inducing sparse measures at vertices in graph-based semi-supervised learning has been accepted at NAACL-HLT 2012.
- Recently, I gave a talk on frame-semantic parsing at several places. Here's a set of slides from the talk I gave at TTI, Chicago.
- Our paper on a nearly universal part-of-speech tagset has been accepted at LREC 2012.
Contact Information:
Email: dipanjand@google.com
Address: 76 9th Avenue,
New York, NY 10011