Mansi Gupta

Machine Learning Engineer @Twitter

Twitter | Blog | LinkedIn | Github | Google Scholar

Hello! I engineer Machine Learning and Natural Language Processing solutions to real world problems. I also dabble in research — I am concerned about unearthing hidden biases in ML systems and strive towards making them fair and interpretable. I aspire to contribute my skills towards developing systems and policies for the next billion under-served population. I live in Pittsburgh PA, with my loving husband Danish, who is pursuing his PhD from Carnegie Mellon University.

Current stint

I work as a part of the Trends and Event Detection team at Twitter where I write algorithms to surface trends and recent events on Twitter, rank them and contextualize them with meaningful information.

Research Papers

Learning to Deceive with Attention-Based Explanations

Danish Pruthi, Mansi Gupta, Bhuwan Dhingra, Graham Neubig, and Zachary C. Lipton

Annual Conference of the Association for Computational Linguistics (ACL), 2020

AmazonQA: A Review-Based Question Answering Task

Mansi Gupta, Nitish Kulkarni, Raghuveer Chanda, Anirudha Rayasam, and Zachary C. Lipton

International Joint Conference on Artificial Intelligence (IJCAI), 2019

Recent stints

Machine Learning Engineer, Petuum

I worked on delivering Machine Learning based solutions to extremely challenging problems on real world noisy datasets. Working in this startup, taught me a lot about how not to run a company.

Machine Learning Algorithms Intern, LinkedIn

I worked on a part of Job Recommendation pipeline where I explored of a new classification technique based on Gaussian Processes and Generalised Linear Mixed Models. This internship taught me a lot about taking statistical models to production.


Carnegie Mellon University, Pittsburgh, PA

Master of Computational Data Science, Computer Science (2017-18)

Birla Institute of Technology and Science, Pilani

Bachelor of Engineering Hons. Computer Science (2011-15)

Past stints

Applied Research Engineer, LinkedIn

I worked in Spam and Relevance team where I worked on modeling propensity of users to spread unprofessional content and analyzed community structure with respect to spread of low quality content on the user graph.

I also worked in the Search team on various projects like building autosuggest and regular search over companies, universities, articles, Slideshare presentations and Lynda courses.