Google Research

Approximating probabilistic models as weighted finite automata

Computational Linguistics, vol. 47 (2021), pp. 221-254

Abstract

Weighted finite automata (WFA) are often used to represent probabilistic models, such as n- gram language models, since they are efficient for recognition tasks in time and space. The probabilistic source to be represented as a WFA, however, may come in many forms. Given a generic probabilistic model over sequences, we propose an algorithm to approximate it as a weighted finite automaton such that the Kullback-Leiber divergence between the source model and the WFA target model is minimized. The proposed algorithm involves a counting step and a difference of convex optimization step, both of which can be performed efficiently. We demonstrate the usefulness of our approach on various tasks, including distilling n-gram models from neural models, building compact language models, and building open-vocabulary character models. The algorithms used for these experiments are available in an open-source software library.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work