Talu Karagöz
2024
An L* Algorithm for Deterministic Weighted Regular Languages
Clemente Pasti
|
Talu Karagöz
|
Franz Nowak
|
Anej Svete
|
Reda Boumasmoud
|
Ryan Cotterell
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Extracting finite state automata (FSAs) fromblack-box models offers a powerful approachto gaining interpretable insights into complexmodel behaviors. To support this pursuit, wepresent a weighted variant of Angluin’s (1987)L* algorithm for learning FSAs. We stay faithful to the original formulation, devising a wayto exactly learn deterministic weighted FSAswhose weights support division. Furthermore,we formulate the learning process in a mannerthat highlights the connection with FSA minimization, showing how L* directly learns aminimal automaton for the target language.
Search