16 March 2019 : I have graduated and my homepage has moved to pushpendre.github.io. This page will not be updated any longer.
I am a CS Ph.D. student in The Center For Language and Speech Processing at the Johns Hopkins University. At CLSP, my advisor is Benjamin Van Durme. I have also had the fortune to work with the following faculty members at JHU: Raman Arora, Kevin Duh, Jason Eisner, Vince Lyzinski, Matt Post, James Spall, and Aaron Steven White.
Selected Publications
See my google scholar profile for a complete list of publications.
- Scaling Multi-Domain Dialogue State Tracking via Query Reformulation. Pushpendre Rastogi, Arpit Gupta, Tongfei Chen and Mathias Lambert. NAACL (2019) [Arxiv Link].
- Neural Variational Entity Set Expansion for Automatically Populated Knowledge Graphs. Pushpendre Rastogi, Adam Poliak, Vince Lyzinski, and Benjamin Van Durme. Information Retrieval Journal (2018). [doi] [bib] .
- Efficient, compositional, order-sensitive n-gram embeddings. Adam Poliak*, Pushpendre Rastogi*, M. Patrick Martin and Benjamin Van Durme, EACL (2017). [pdf] [bib](* indicates equal contribution)
- Vertex Nomination on the Cold Start Knowledge Graph. Pushpendre Rastogi, Vince Lyzinski, and Benjamin Van Durme (2017). Technical report, HLTCOE (2017). [pdf] [bib]
- Weighting Finite-State Transductions With Neural Context, Pushpendre Rastogi, Ryan Cotterell, Jason Eisner. NAACL(2016) [bib] [pdf] [slides] [code]
- Efficient Implementation of Enhanced Adaptive Simultaneous Perturbation Algorithms. Pushpendre Rastogi, Jingyi Jhu, James Spall. CISS(2016) [bib] [code] [pdf]
- Multiview LSA: Representation Learning Via Generalized CCA. Pushpendre Rastogi, Benjamin Van Durme and Raman Arora, NAACL(2015) [pdf], [data+code], [bib], [poster], [supplementary]
- Stationarity Condition for Fractional Sampling Filters. Pushpendre Rastogi (Master's theses)[pdf]
Posts
- Searchable PDF version of the Penn Treebank Bracketing Guideline
- Matrix Decompositions
- Beginners analysis for optimization in Data Science.
- The impossibility of specifying the number of samples needed in a validation set using t-distributions for regression with unbounded loss
- Induction and Recursion
- Understanding Logistic Regression II
- Convex Neural Networks?
- Online Sample Complexity Bound Calculator
- Class Diagram Portion From Uml
- Multiview LSA Motivation and Proofs
- Mathematical Notation Glossary
- Eigenvalue Problems