Reversibility reconsidered: finite-state factors for efficient probabilistic sampling in parsing and generation

Marc Dymetman, Sriram Venkatapathy, Chunyang Xiao

Abstract: We restate the classical logical notion of generation/parsing reversibility in terms of feasible probabilistic sampling, and argue for an implementation based on finite-state factors. We propose a modular decomposition that reconciles generation accuracy with parsing robustness and allows the introduction of dynamic contextual factors. (Opinion Piece)