Abulhair Saparov

8003 Gates Hillman Ctr
5000 Forbes Avenue
Pittsburgh, PA 15213

Hello! I am a Ph.D. student in the Machine Learning Department at Carnegie Mellon University. I am advised by Professor Tom Mitchell.

My research focuses on applications of statistical machine learning to natural language processing (NLP), natural language understanding (NLU), and reasoning. More specifically, I developed generative probabilistic models of grammar to train semantic parsers (i.e. how can a machine learn to convert natural language into logical forms?) and generate natural language utterances from logical forms (i.e. how can a machine learn to convert logical forms into natural language?). I have recently worked on algorithms to abduce world models (i.e. theories) from logical forms (which, in turn, are produced from semantic parsers), and to utilize/reason over previously-acquired knowledge to perform downstream tasks, such as question-answering. I am also interested in symbolic representations of meaning and reasoning in the context of NLU. In my work, I have applied Bayesian nonparametrics, approximate posterior inference, and combinatorial optimization. I am also broadly interested in other applications of statistical machine learning.

Prior to CMU, I received a B.S.E. in Computer Science at Princeton University with certificates (minors) in Applied Mathematics and Neuroscience.