Parth Gupta


Experience Publications Code Contact
I build scalable and delightful Search systems with cutting edge ML technologies. I manage Search and Ranking tech teams to deliver high impact customer facing results. Over past 15 years, worked on several Search systems including Learning to Rank, L1/L2 Rankers, Semantic Matching, Query Understanding and Autocompletion, Search Relevance/Defects, Cold-start, Multilingual Search, Product Recommendation and Discovery at leading search engines (Coupang Search, Amazon Search, Microsoft Bing, Xapian). Based in SF Bay Area, in the middle of Search revolution.



Research Interests

Information retrieval, machine learning, text mining, statistical natural language processing, deep-learning, data science

Updates

(Not updated actively)
  • Oct, 2022: Paper accepted at CIKM 2022 on Bayesian methods to address sold-start in Product Search (details)
  • Mar, 2022: Paper accepted at SIGIR 2022 on role of clicks in ranking and unbiased learning to rank
  • Jun, 2021: Paper accepted at CIKM 2021 on seasonal relevance in Produc Search
  • Jan, 2020: Poster paper accepted at WWW 2020 on cold-start in Search
  • July, 2019: Attended SIGIR 2019 in Paris
  • July 2019: Organised 2nd Edition of Search Workshop at Amazon ML Conference 2019 in Seattle
  • May, 2019: Attended WWW 2019 in San Francisco
  • November, 2018: Have moved to Amazon Search Science and AI team (A9) in Palo Alto.
  • June, 2018: Invited to co-chair Demo track at CODS-COMAD 2019.
  • March, 2018: Gave an invited talk at IIT Kharagpur on Machine Learning at Amazon
  • March, 2018: Gave a couple of Guest Lectures in Machine Learning course at IIT Kharagpur (details)
  • Feb, 2018: Short paper accepted at WWW 2018
  • Jan, 2018: Attended CODS-COMAD Conference in Goa
  • Nov, 2017: Gave a talk on Deep Learning at GHCI 2017. (Details)
  • Sept, 2017: Gave a tutorial on distributed training using MXNet at Amazon India AI Summit in Bangalore.
  • March, 2017: Joined Core ML team at Amazon as ML Scientist to take on cutting-edge ML research
  • Jan, 2017: Successfully defended PhD thesis
  • Dec, 2016: Paper accepted at ECIR 2017 titled "Learning to classify inappropriate query-completions"
  • Dec, 2016: Paper accepted at Information Processing & Management titled "Continuous space models for CLIR"
  • Dec 07, 2016: Tutorial on "Deep Learning for Information Retrieval" at FIRE 2016, Kolkata, India
  • Nov 03, 2016: Visited Search team of Wikimedia Foundation, San Francisco, USA
  • Nov 02, 2016: Talk at Bay Area NLP Meetup @ Galvanize, San Francisco, USA
  • Oct 28-30, 2016: Participating in GSoC Mentor Summit at Google (Mountain View), USA
  • Set 22, 2016: PhD thesis submitted
  • June, 2016: Patent based on work at Microsoft Bing (London) has been filed at USPTO

Experience