Simple induction of (deterministic) probabilistic finite-state automata for phonotactics by stochastic gradient descent

Huteng Dai, Richard Futrell


Abstract
We introduce a simple and highly general phonotactic learner which induces a probabilistic finite-state automaton from word-form data. We describe the learner and show how to parameterize it to induce unrestricted regular languages, as well as how to restrict it to certain subregular classes such as Strictly k-Local and Strictly k-Piecewise languages. We evaluate the learner on its ability to learn phonotactic constraints in toy examples and in datasets of Quechua and Navajo. We find that an unrestricted learner is the most accurate overall when modeling attested forms not seen in training; however, only the learner restricted to the Strictly Piecewise language class successfully captures certain nonlocal phonotactic constraints. Our learner serves as a baseline for more sophisticated methods.
Anthology ID:
2021.sigmorphon-1.19
Volume:
Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | SIGMORPHON
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
167–176
Language:
URL:
https://aclanthology.org/2021.sigmorphon-1.19
DOI:
10.18653/v1/2021.sigmorphon-1.19
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.sigmorphon-1.19.pdf