Sonal Gupta

Sonal Gupta

PhD Candidate

Department of Computer Science

Stanford University

[First Name]-{at}-cs-[dot]-stanford-"dot"-edu

Home Research Software and Data Teaching Education Work Personal Contact

I am a PhD student in Computer Science at Stanford University. I am planning to graduate in summer 2015. I work with Christopher D. Manning in the Stanford Natural Language Processing (NLP) group. I have collaborated with Diana MacLean, Sanjay Kairam, and Jason Chuang from the Interactive Data Lab under Jeffrey Heer. For my Master's thesis at UT Austin, I worked on combining NLP and computer vision with Ray Mooney and Kristen Grauman. Here is my (probably outdated) resume.



  • Induced Lexico-Syntactic Patterns Improve Information Extraction from Online Medical Forums.
    Sonal Gupta, Diana MacLean, Jeffrey Heer, and Christopher D. Manning.
    Journal of the American Medical Informatics Association (JAMIA). 2014.
    pdf (email me for a copy if you are not able to access it)

  • Prescription Opioid Addicts Seek Advice on Opioid Withdrawal from Peers Online.
    Diana MacLean, Sonal Gupta, Anna Lembke, Christopher D. Manning, and Jeffrey Heer.
    Under Review. 2014

Conferences and Workshops

Work Experience

Summer 2012: Data Science Intern, PayPal Inc. Modeled sentiment of PayPal's customer feedback data by learning topic models. Mentor: Junling Hu.
Summer 2008: Research Intern, Microsoft Research. Proposed and implemented an online learning algorithm, Amnesiac Averaged Perceptron, to learn arbitrary similarity functions as features using clickthrough logs. Mentors: Misha Bilenko and Matthew Richardson.
Summer 2006: Software Intern, Google R&D Center, Bangalore. Implemented boosting machine learning technique in the MapReduce framework, using sequential and parallel update, for classifying shopping web pages. Mentor: Vineet Gupta



FTD dataset and seed patterns from the paper Analyzing the Dynamics of Research by Extracting Key Aspects of Scientific Papers.



I graduated from the University of Texas at Austin with a Master's (thesis option) in Computer Science. At UT, I worked with Dr. Ray Mooney on combining text and visual perception. Before that, I did my B.Tech. degree at Indian Institute of Technology (IIT) Roorkee, India in Computer Science and Engineering. IIT Roorkee (formerly University of Roorkee and Thomson College of Engineering) is the oldest engineering college in India. At IIT-R, I worked with Dr. Kumkum Garg and Dr. R. C. Joshi.

In the grad school, I have taken following relevant courses:

(Social and Information) Network Analysis; Probabilistic Graphical Models; Convex Optimization;Machine Learning; Computer Vision; Visual Recognition and Search; Networks, Protocol and Security; Natural Language Processing; Numerical Linear Algebra; Modern Statistical Methods; Introduction to Math Logic



I was born and brought up in a beautiful and quiet city-Bhopal, India. Unfortunately, it is known for Bhopal Gas Tragedy. Bhopal is sometimes called 'City of Lakes' as it has many natural and man-made lakes. I did my schooling from Jawahar Lal Nehru School. In 2003, I moved to Roorkee to study Computer Science at IIT Roorkee . Roorkee is a small town near Haridwar, Dehradun and Hrishikesh. I enjoyed my four years at Roorkee to fullest with frequent trips to near-by hill stations at the foothill of Himalayas (Rishikesh, Shimla, Manali, Auli, Mussoorie, Dehradun, Haridwar etc.). IIT Roorkee is also a nice place to be to do white water rafting at Ganges, with IITR bearing most of the cost :)

Lately, I have been biking, swimming, and running (my weakest of the three). I hope to do a triatholon some day soon. When I have too much free time (i.e. almost never these days), I like to paint; some of the paintings can be seen here.

One of my main weaknesses is good spicy (mostly vegetarian) food, with the favorites being: Indian, Mexican, Indian Chinese and Thai. I like to learn new cuisines and cook at home.


Asha for Education, Stanford

My undergrad college: IIT Roorkee

Some best moments of my life: Information Management Group

My Pics: Picasa Web Album

Some Interesting Links

Indian English, which I find to be quite different from American English! Well, my favorite language is Hinglish. I think it will be interesting to study Hinglish as a language.


Email Address: see top of the page

Postal Address: Computer Science Department
353 Serra Mall, Stanford University
Stanford, CA 94305

Office Location: Gates 233