I am a post-doctoral researcher at Microsoft Research New York City. I work in the interdisciplinary area of interpretable and interactive machine learning. I am passionate about studying human behavior when interacting with machine learning models. I am interested in using these insights to design machine learning models that humans can use effectively. I am also interested in several aspects of fairness, accountability, and transparency in machine learning and their effect on users’ decision-making process.

Before joining Microsoft, I got my PhD in computer science from the University of Colorado at Boulder, where I was advised by Jordan Boyd-Graber . Before that, I got my BE in computer engineering from the University of Tehran.

My research statement outlines my interests and ambitions.


  • [September 2018] I will give a talk at the Machine Learning Conference on November 14th.
  • [December 2017] I will present Manipulating and Measuring Model Interpretability in a workshop at NIPS.
  • [October 2017] I will present an abstract of my internship project in WiML at NIPS. Come see my poster on Manipulating and Measuring Model Interpretability.
  • [March 2017] I will be a research intern at MSR NYC this summer. I am going to be working on machine learning interpretability!
  • [September 2016] I spent a great summer as an intern in IRML group at Oracle Labs. I worked on semi-supervised text classification using feature labels and topic models.
  • [May 2016] Our paper on using active learning and topic models for speeding label induction and document labeling was accepted in ACL 2016.
  • [April 2016] Our paper on evaluating visual representations for topics was accepted in TACL 2016.