I joined the Dialog State Tracking in Amazon Alexa in April 2019. I completed my Ph.D. in Computer Science at The Center For Language and Speech Processing, Johns Hopkins University. My advisor was Benjamin Van Durme. I TA'd graduate courses on representation learning and machine learning for three semesters during my Phd studies, and I received the George Sommerman Graduate Teaching Assistant Award with a cash award of $1000. I have reviewed for Transactions On Signal Processing-19, NEURIPS-19, ICML-19, ICLR-19, EMNLP-19, ACL-19, TPAMI-18, NeurIPS-18, KG4IR-18, EMNLP-18, ACL-18.
See my google scholar profile for a complete list of publications.
- "Improving long distance slot carryover in spoken dialog systems".Tongfei Chen, Chetan Naik, Hua He, Pushpendre Rastogi, and Lambert Mathias. (2019) [arxiv] [bestpaper]
- "Scaling Multi-Domain Dialogue State Tracking via Query Reformulation".Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, and Lambert Mathias. (2019) [arxiv] [chinese-translation-1] [chinese-translation-2] [dataset] [press-venturebeat]
- "A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (cqr)".Michael Regan, Pushpendre Rastogi, Arpit Gupta, and Lambert Mathias. (2019) [arxiv] [dataset]
- "Neural variational entity set expansion for automatically populated knowledge graphs".Pushpendre Rastogi, Adam Poliak, Vince Lyzinski, and Benjamin Van Durme. (2018) [bib] [doi] [code] [demo]
- "Efficient, compositional, order-sensitive n-gram embeddings".Adam Poliak, Pushpendre Rastogi, M. Patrick Martin, and Benjamin Van Durme. (2017) [pdf] [bib] [code] [poster]
- "Vertex nomination on the cold start knowledge graph".Pushpendre Rastogi, Vince Lyzinski, and Benjamin Van Durme. (2017) [pdf] [bib]
- "Weighting finite-state transductions with neural context".Pushpendre Rastogi, Ryan Cotterell, and Jason Eisner. (2016) [bib] [pdf] [slides] [code]
- "Efficient implementation of enhanced adaptive simultaneous perturbation algorithms".Pushpendre Rastogi, Jingyi Zhu, and James Spall. (2016) [bib] [code] [pdf] [nevergrad]
- "Multiview lsa: Representation learning via generalized cca".Pushpendre Rastogi, Benjamin Van Durme, and Raman Arora. (2015) [pdf] [data] [code] [bib] [poster] [supplementary]
- "Stationarity condition for fractional sampling filters".Pushpendre Rastogi. (2011) [pdf]
|Ph.D. and M.S. in Computer Science||Johns Hopkins University||2013-19||3.75/4.0|
|Thesis Topic: Representation Learning for Words and Entities. I presented new methods for unsupervised learning of word and entity embeddings from texts and knowledge bases.|
Courses and Grades: Natural Language Processing (A), Machine Learning in Complex Domains (A), Stochastic Search & Optimization (B), Parallel Programming (A-), Principles of Programming Languages (A-), Combinatorial Optimization (A+), Introduction to Convexity (A-)
|M.Tech. in Information and Communication Technology||IIT Delhi||2010-11||8.77/10|
|B.Tech. in Electrical Engg.||IIT Delhi||2006-10||8.86/10|
Technical NotesAll notes are also hosted in a dropbox folder.
|Note 1 Describes how the variance of an AB test can be reduced in the special case when we are comparing two policies with the same small-finite action space. [PDF]|
|Note 2 A video tutorial - primarily for my own understanding - about the difference between PnL and Cashflow, and how a company can have positive cash flow but still make loss, without raising debt. (you may need to download the video and play with VLC)|
|Note 3 [WIP] A visual proof of the UCB algorithm.|