Encoder-decoder models for latent phonological representations of words

Cassandra L. Jacobs, Frédéric Mailhot


Abstract
We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words. We show that the output of an encoder network can predict the phonetic durations of American English words better than a number of alternative forms. We also show that the model’s learned representations map onto existing measures of words’ phonological structure (phonological neighborhood density and phonotactic probability).
Anthology ID:
W19-4224
Volume:
Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Garrett Nicolai, Ryan Cotterell
Venue:
ACL
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
206–217
Language:
URL:
https://aclanthology.org/W19-4224
DOI:
10.18653/v1/W19-4224
Bibkey:
Cite (ACL):
Cassandra L. Jacobs and Frédéric Mailhot. 2019. Encoder-decoder models for latent phonological representations of words. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 206–217, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Encoder-decoder models for latent phonological representations of words (Jacobs & Mailhot, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4224.pdf