In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology

Chundra Cathcart, Florian Wandl


Abstract
This paper investigates the ability of neural network architectures to effectively learn diachronic phonological generalizations in amultilingual setting. We employ models using three different types of language embedding (dense, sigmoid, and straight-through). We find that the Straight-Through model out-performs the other two in terms of accuracy, but the Sigmoid model’s language embeddings show the strongest agreement with the traditional subgrouping of the Slavic languages. We find that the Straight-Through model has learned coherent, semi-interpretable information about sound change, and outline directions for future research.
Anthology ID:
2020.sigmorphon-1.28
Volume:
Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
July
Year:
2020
Address:
Online
Editors:
Garrett Nicolai, Kyle Gorman, Ryan Cotterell
Venue:
SIGMORPHON
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
233–244
Language:
URL:
https://aclanthology.org/2020.sigmorphon-1.28
DOI:
10.18653/v1/2020.sigmorphon-1.28
Bibkey:
Cite (ACL):
Chundra Cathcart and Florian Wandl. 2020. In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 233–244, Online. Association for Computational Linguistics.
Cite (Informal):
In search of isoglosses: continuous and discrete language embeddings in Slavic historical phonology (Cathcart & Wandl, SIGMORPHON 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.sigmorphon-1.28.pdf
Video:
 http://slideslive.com/38929873