Interpreting Finite Automata for Sequential Data
This work addresses interpretability in automata for researchers and practitioners in sequential data analysis, but it appears incremental as it builds on existing state-merging methods.
The paper tackles the problem of defining interpretability for automaton models by identifying key properties and modifying a state-merging approach to learn finite state automata variants, applying it to tasks beyond grammar inference like prediction, classification, and clustering on sequential data.
Automaton models are often seen as interpretable models. Interpretability itself is not well defined: it remains unclear what interpretability means without first explicitly specifying objectives or desired attributes. In this paper, we identify the key properties used to interpret automata and propose a modification of a state-merging approach to learn variants of finite state automata. We apply the approach to problems beyond typical grammar inference tasks. Additionally, we cover several use-cases for prediction, classification, and clustering on sequential data in both supervised and unsupervised scenarios to show how the identified key properties are applicable in a wide range of contexts.