Rishabh Mehrotra

AI Researcher

Hi, i'm Rishabh Mehrotra!

Computer Scientist & Researcher


CS PhD candidate at University College London. Interested in teaching machines to better understand, comprehend & support user needs.

r.mehrotra@cs.ucl.ac.uk

Updates

  • [April, 2017] 2 full papers accepted at SIGIR 2017.
  • [Feb, 2017] Poster on Session identification for Intelligent Assistants accepted at WWW 2017 Posters track.
  • [Jan, 2017] Full paper on Combining Bayesian Nonparametrics & deep embeddings for extracting subtasks accepted at WWW 2017 Cognitive track.
  • [Dec, 2016] Full paper on Auditing search engines for systemic bias accepted at WWW 2017.
  • [Nov, 2016] Gave a tutorial on Inferring User Tasks & Needs at Search Solutions 2016.
  • [July, 2016] Excited to be working on Cortana with Imed Zitouni & Ahmed Hassan at Microsoft Research, Redmond.
  • [June, 2016] Gave an invited talk on Digital Assistants, Proactive Recommendations & Search Tasks at Machine Learning meetup, Gurgaon.
  • [June, 2016] Paper accepted at ECML 2016.
  • [April, 2016] We're organizing the TREC 2016 Tasks Track. Consider participating!
  • [March, 2016] Excited to be working with Fernando Diaz on Fairness in Machine Learning/IR at Microsoft Research, New York.
  • [March, 2016] Our short paper on task based heterogeneities in user behavior accepted at SIGIR'16.
  • [March, 2016] Our work on complex search tasks accepted at NAACL'16.
  • Education

    • University College London 2014 - current

      Ph.D. in Computer Science

      Dept. of Computer Science

      Advisor: Dr. Emine Yilmaz

      Area: Machine Learning, Information Retrieval

    • BITS Pilani2008 - 2013

      B.E.(Hons.) Computer Science

      M.Sc.(Hons.) Mathematics

      Thesis: Sparsity & Structured Sparsity for Learning Coupled Representations from Multi-View Data

    Research Experience

    • Sept'16 June'16

      Microsoft Research, Redmond

      Research Intern, Measurement Sciences Team
      Mentors: Imed Zitouni, Ahmed Hassan
      Description: Developed terascale machine learning based solutions for understanding user interaction sequences for satisfaction prediction. Mining terabytes of logs for developing task based satisfaction metrics.


    • June'16 March'16

      Microsoft Research, New York

      Research Intern, Machine Learning Group
      Mentors: Fernando Diaz
      Description: Developed techniques for auditing search engines for demographic bias in performance.


    • Sept'15 July'15

      Microsoft Research, Redmond

      Research Intern, CLUES Group
      Mentors: Susan Dumais, Paul Bennett
      Description: Responsible for designing and developing terascale machine learning based solutions for cross-domain personalization. Mining terabytes of user logs to derive insights for personalization.


    • June'15 April'15

      Microsoft Bing, London

      Applied Scientist Intern, Related Searches Team
      Mentors: Abhishek Arun, Katja Hofmann
      Description: Developed techniques for counterfactual estimation of online metrics.


    • Dec'13 June'13

      Goldman Sachs, Bangalore

      Techology Analyst Reference Data Team
      Description: Developed Regression Testing framework for an event-driven SOA based framework.


    • Aug'12 May'12

      Google Summer of Code (GSoC)

      Xapian: search engine library
      Description: Implemented Learning to Rank algorithms for LETOR framework.


    • July'12 May'12

      NICTA, Australia

      Machine Learning Intern
      Mentors: Scott Sanner, Wray Buntine
      Description: Improving LDA topic models for microblogs.

    PUBLICATIONS

    2017

    Extracting & Leveraging User Interaction Sequences for Search Satisfaction Prediction
    Rishabh Mehrotra, Imed Zitouni, Ahmed Hassan Awadallah and Ahmed El Kholy
    SIGIR 2017

    Extracting Hierarchies of Search Tasks \& Subtasks via a Bayesian Nonparametric Approach
    Rishabh Mehrotra and Emine Yilmaz
    SIGIR 2017

    Auditing Search Engines for Differential Performance Across Demographics
    Rishabh Mehrotra, Ashton Anderson, Fernando Diaz, Amit Sharma, Hanna Wallach and Emine Yilmaz
    WWW 2017

    Identifying User Sessions in Interactions with Intelligent Assistants
    Rishabh Mehrotra, Imed Zitouni, Ahmed Hassan Awadallah, Milad Shokouhi and Ahmed El Kholy
    WWW 2017 (Posters Track)

    2016

    Query Log Mining for Inferring User Tasks and Needs
    Rishabh Mehrotra and Emine Yilmaz
    ECML 2016 (Nectar Track)

    Uncovering Task Based Behavioral Heterogeneities in Online Search Behavior
    Rishabh Mehrotra, Prasanta Bhattacharya and Emine Yilmaz
    SIGIR 2016

    Characterizing Cross-Domain Search Behavior
    Rishabh Mehrotra, Paul N. Bennett, Susan Dumais, Jaime Teevan
    HIA @ SIGIR 2016

    Deconstructing Complex Search Tasks
    Rishabh Mehrotra, Prasanta Bhattacharya and Emine Yilmaz
    NAACL 2016

    Characterizing Users' Multi-Tasking Behavior in Web Search
    Rishabh Mehrotra, Prasanta Bhattacharya and Emine Yilmaz
    CHIIR 2016

    The Information Network: Exploiting Causal Dependencies in Online Information Seeking
    Prasanta Bhattacharya, Rishabh Mehrotra
    CHIIR 2016

    2015

    Representative & Informative Query Selection for Learning to Rank using Submodular Functionsd Needs
    Rishabh Mehrotra and Emine Yilmaz
    SIGIR 2015

    Terms, Topics & Tasks: Enhanced User Modelling for Better Personalization
    Rishabh Mehrotra and Emine Yilmaz
    ICTIR 2015

    Modeling the Evolution of User-generated Content on a Large Video Sharing Platform
    Rishabh Mehrotra, Prasanta Bhattacharya
    WWW 2015 (Web Science Track)

    Towards Hierarchies of Search Tasks & Subtasks
    Rishabh Mehrotra and Emine Yilmaz
    WWW 2015 (Posters track)

    Overview of the TREC 2015 Tasks Track
    Emine Yilmaz, Evangelos Kanoulas, Manisha Verma, Nick Craswell, Rishabh Mehrotra
    TREC 2015

    Topics, Tasks & Beyond: Learning Representations for Personalization
    Rishabh Mehrotra
    WSDM 2015 (Doctoral Consortium)

    A Tensor Based Approach for Coupling Search Tasks and Topical Interests for User Modelling
    Rishabh Mehrotra, Emine Yilmaz
    HIA @ WSDM 2015

    2014 & before

    Task-Based User Modelling for Personalization via Probabilistic Matrix Factorization
    Rishabh Mehrotra and Emine Yilmaz
    RecSys 2014

    Improving LDA Topic Models for Microblogs via Automatic Tweet Labeling and Pooling.
    Rishabh Mehrotra, Scott Sanner, Wray Buntine, Lexing Xie,
    SIGIR 2013

    Towards Learning Coupled Representations for Cross-Lingual Information Retrieval
    Rishabh Mehrotra, Dat Chu, Syed Aqueel Haider, Iaonnis Kakadiaris
    xLiTe @ NIPS 2012

    Dictionary based Sparse Representation for Domain Adaptation
    Rishabh Mehrotra, Rushabh Agrawal, Syed Aqueel Haider
    CIKM 2012

    Corporate News Classification and Valence Prediction: A Supervised Approach
    Syed Aqueel Haider, Rishabh Mehrotra
    WASSA @ ACL 2011

    Neural Self-Organization based Rectilinear Steiner Minimal Tree Generation in 3 Dimensions
    Rushabh Agrawal, Rishabh Mehrotra, AS Mandal
    ICMS 2012