Parameter estimation for probabilistic finite-state transducers

Abstract

Weighted finite-state transducers suffer from the lack of a training algorithm. Training is even harder for transducers that have been assembled via finite-state operations such as composition, minimization, union, concatenation, and closure, as this yields tricky parameter tying. We formulate a "parameterized FST" paradigm and give training algorithms for it, including a general bookkeeping trick ("expectation semirings") that cleanly and efficiently computes expectations and gradients.