Excited to be joining BenevolentAI lab in NYC to use NLP and AI for the great mission of accelerating drug discovery for major diseases and more. If you are interested in research opportunities in our lab, consider applying here.

Nasrin Mostafazadeh

Department of Computer Science
University of Rochester
Rochester, NY
Email: nasrinm [at] cs [dot] rochester [dot] edu

I'm Nasrin Mostafazadeh and recently defended my PhD at the Computer Science department of University of Rochester with the title of "From Event to Story Understanding". At Rochester I worked under James F. Allen in Conversational Interaction and Spoken Dialogue Research Group.

I'm interested in building intelligent systems which can understand the language (hopefully deeply!). I mainly model language in terms of 'events' and how they interact with each other in time, with applications ranging from story understanding to vision & language. Deep language understanding, which enables inference and commonsense reasoning, requires systems that have large amounts of knowledge enabling them to connect natural language to the concepts of the world. A part of my work concerns developing approaches for learning semantically rich knowledge bases on events and their causal and temporal relations.

I run the Big-Picture Talk Series at Rochester (occasionally, these talks are unofficially live streamed). I am also a member of Center for Language Sciences at Rochester. I spent summer 2016, spring 2016, and summer 2015 at Microsoft Research Redmond mentored by Lucy Vanderwende, working with Michel Galley, Xiaodong He, Margaret Mitchel and Pushmeet Kohli on vision & language. I spent summer 2014 at Google NYC working on Sentiment Analysis under Ian Langmore and mentored by Emily Pitler. I've got my bachelor's degree from Sharif University of Technology in 2012 where I was a member of NLP lab under Gholamreza Ghassem-Sani . I have been graduated from Farzanegan high school where I started my work in NLP and AI. For more detailes, please refer to my CV.

Recent Events

LSDSem 2017

We organized Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem) workshop, with the Story Cloze Test as the shared task. Visit the Shared Task page for more details.


Past Events

QA TempEval 2015

We organized Question Answering Temporal Evaluation (QA TempEval) as the task 5 at SemEval-2015, continuing the TempEval series. Visit the page for more details.

Thought bubble! Quite a long time ago, I got interested in Computational Linguistics when I read about Noam Chomsky's theory of Innate Universal Grammar, when I was amazed by how language capability (seemingly the easiest for human) is the hardest to achieve for a robot (which could readily prove things like geometry theorems, which seemed harder to me at the time!). After you watch this video, don't you wish we had NLP systems which could actually tell us 'why', going beyond recognizing patterns and classifying things? and of course the question is how...