Grasp: Randomised Semiring Parsing

Wepresent a suite of algorithms for inference tasks over (finite and infinite) context-free sets. For generality and clarity, we have chosen the framework of semiring parsingwith support to the most common semirings (e.g. F, V, k- and I). We see parsing from themore general viewpoint of weighted deduction allowing for arbitrary weighted finite-state input and provide implementations of both bottom-up (CKY-inspired) and top-down (E-inspired) algorithms. We focus on approximate inference by Monte Carlo methods and provide implementations of ancestral sampling and slice sampling. In principle, sampling methods can deal with models whose independence assumptions are weaker than what is feasible by standard dynamic programming. We envision applications such as monolingual constituency parsing, synchronous parsing, context-free models of reordering for machine translation, and machine translation decoding.