Jason Eisner


Primary Appointment:  Department of Computer Science

Research Interests

  • Natural language and speech processing
  • New machine learning
  • Combinatorial algorithms
  • Probabilistic models of linguistic structure
  • Declarative specification of knowledge and algorithms

A professor of computer science, Eisner is affiliated with the Center for Language and Speech Processing and the Human Language Technology Center of Excellence, and leads JHU’s cross-departmental machine learning group. His goal is to develop the probabilistic modeling, inference, and learning techniques needed for a unified model of all kinds of linguistic structure. Eisner has written more than 100 papers in several areas of computational linguistics, especially parsing, grammar induction, machine translation, computational phonology, computational morphology, and weighted finite-state methods. He is also the lead designer of Dyna, a new declarative programming language that provides an infrastructure for AI research.

Secondary Appointments: Cognitive Science

Center for Language and Speech Processing