Uma Sawant

Office: Infolab, Kresit lab 212,
Department of Computer Science and Engineering
IIT Bombay
Mumbai 400 076
Email: uma AT cse DOT iitb DOT ac DOT in

Short Bio

I am a PhD candidate in the Computer Science and Engineering department of IIT Bombay, since Autumn 2011. My advisor is Prof. Soumen Chakrabarti. I was also fortunate to work with Dr. Peter Mika and Dr. Roi Blanco from Yahoo! Labs, Barcelona.

Prior to joining PhD program, I was working as a research engineer at Yahoo! labs, Bangalore. I obtained a master's degree from CSE department, IIT Bombay, in 2008. Here is my resume in html and pdf.

Research Topic

Web search views the Web as a collection of documents and returns a list of documents ranked in the order of relevance to the user query. Identification of objects or concepts in a document (people, places, cars etc) allows us to do more; such as providing direct answers to many user queries. I am interested in this kind of "Entity search". I am currently studying the query interpretation and ranking components for the same.


  • Uma Sawant, Vijay Gabale, E-fashion Product Discovery via Deep Text Parsing. WWW 2017, Perth, Australia. [poster]
  • Mandar Joshi, Uma Sawant, Soumen Chakrabarti, Knowledge Graph and Corpus Driven Segmentation and Answer Inference for Telegraphic Entity-seeking Queries. EMNLP 2014, Doha, Quatar. [pdf][ppt]
  • Uma Sawant, Soumen Chakrabarti, Learning Joint Query Interpretation and Response Ranking. In proceedings of WWW 2013, Rio De Janeiro, Brazil. [pdf][ppt]
  • Uma Sawant, Soumen Chakrabarti, Features and Aggregators for Web-scale Entity Search. Technical report, 2013. [arxiv]
  • Soumen Chakrabarti, Rajiv Khanna, Uma Sawant, Chiru Bhattacharyya, Structured Learning for Non-Smooth Ranking Losses. In proceedings of KDD-2008, Las Vegas. [pdf]
  • Aniket Dalal, Kumar N., Uma Sawant, Sandeep Shelke and Pushpak Bhattacharyya, Building Feature Rich POS Tagger for Morphologically Rich Languages: Experiences in Hindi. In proceedings of ICON 2007, IIIT, Hyderabad. [pdf]


  • "Introduction to Entity Search", talk at Machine Learning India meetup, Bangalore, February 2017. slides.
  • "Demystifying deep learning", workshop at GHC 2016, Houston, October 2016.
  • Invited webinar on Deep learning at IIT Guwahati, as a part of data mining lecture series by Prof. Amit Awekar, October 2016.
  • "Spam filtering at scale", talk at Workshop on Analysis and Inference from UGC (WAIU), IISc Bangalore, 28 March, 2016
  • Talk at Deep Learning meetup, Bangalore. 14 February, 2016
  • Seminar at IIT Kanpur, 21 August 2014
  • "Learning Joint Query Interpretation and Response Ranking". Poster accepted in Grace Hopper Celebration 2013, Minneapolis, Minnesota.
  • Presentation at Yahoo summer school 2013
  • Yahoo!'s Team Superstar Award (Yahoo, Inc.), 2010.
  • Google India Women In Engineering award (2008)
  • Part of the 4-member team of IIT Bombay which secured second prize in NLPAI-ML 2006 contest for shallow parsing of Indian languages, a national level contest in the field of natural language processing.

    Something About Me

    I love books, music and tv/film adaptations of classic british literature. I am a big fan of P. L. Deshpande, Sherlock Holmes and Jane Austen. As a hobby, I am learning Hindusthani classical vocal.
    My sister and I are mentioned one after the other in the reviewer's list. How cool is that!
    Visit some of my CS PhD friends : Neela, Meghana, Bhavana, Arun, Sujesha, Pratik, Swetha, Karthik, Vijay.

    Fun : Research in progress, PhD comics
    Something to think about: Pawel Kuczynski's satirical illustrations, 1/2 == 1/3 == 1/4?
    Public Datasets