Analyzing Correlated Evolution of Multiple Features Using Latent Representations

Yugo Murawaki


Abstract
Statistical phylogenetic models have allowed the quantitative analysis of the evolution of a single categorical feature and a pair of binary features, but correlated evolution involving multiple discrete features is yet to be explored. Here we propose latent representation-based analysis in which (1) a sequence of discrete surface features is projected to a sequence of independent binary variables and (2) phylogenetic inference is performed on the latent space. In the experiments, we analyze the features of linguistic typology, with a special focus on the order of subject, object and verb. Our analysis suggests that languages sharing the same word order are not necessarily a coherent group but exhibit varying degrees of diachronic stability depending on other features.
Anthology ID:
D18-1468
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4371–4382
Language:
URL:
https://aclanthology.org/D18-1468/
DOI:
10.18653/v1/D18-1468
Bibkey:
Cite (ACL):
Yugo Murawaki. 2018. Analyzing Correlated Evolution of Multiple Features Using Latent Representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4371–4382, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Analyzing Correlated Evolution of Multiple Features Using Latent Representations (Murawaki, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1468.pdf
Attachment:
 D18-1468.Attachment.pdf
Video:
 https://aclanthology.org/D18-1468.mp4
Code
 murawaki/lattyp