I am a research scientist in the Language and Translation Technologies team at Facebook AI Applied Research. I develop novel machine learning solutions for natural language understanding problems. I build AI applications that interact with and learn from people.
My recent research has been under the following themes:

Natural Language Driven Mixed-Initiative Human-Machine Interaction: Learning to map user utterances to executable machine instructions in complex scenarios; building natural language powered software interfaces.
Joint Representation of Textual and Symbolic Knowledge: Learning novel representations that effectively contextualize textual and symbolic knowledge to power downstream AI systems.
Fairness and Accountability: Mitigating unwanted biases in machine learning models; uncertainty modeling in decision making; uncovering social biases via statistical methods.
Previously I was a senior research scientist at Salesforce Research, where I led Photon and other projects in semantic parsing. I was a graduate student at the Paul G. Allen School of Computer Science & Engineering, University of Washington, working with Luke Zettlemoyer and Michael D. Ernst on data-driven natural language programming.