Forough Arabshahi

Research Scientist

I am a Research Scientist at Facebook. My research focuses on developing sample efficient learning algorithms for automated and commonsense reasoning. My research addresses three main challenges in reasoning, namely, (1) zero-shot generalization (2) Explainability and (3) Conversational Instructability. My expertise are in developing neuro-symbolic learning algorithms, recursive neural networks, latent variable models, tensor methods, and probabilistic graphical models. I am also interested in natural language processing where I focus on conversational machine learning, and have developed semantic parsing algorithms and conversational knowledge base editing methods.

Prior to joining Facebook, I was a postdoctoral researcher at the Machine Learning Department at Carnegie Mellon University with Tom Mitchell. I obtained my PhD from the University of California Irvine under the supervision of Anima Anandkumar and Sameer Singh.