A Bayesian Model of Diachronic Meaning Change

Lea Frermann, Mirella Lapata


Abstract
Word meanings change over time and an automated procedure for extracting this information from text would be useful for historical exploratory studies, information retrieval or question answering. We present a dynamic Bayesian model of diachronic meaning change, which infers temporal word representations as a set of senses and their prevalence. Unlike previous work, we explicitly model language change as a smooth, gradual process. We experimentally show that this modeling decision is beneficial: our model performs competitively on meaning change detection tasks whilst inducing discernible word senses and their development over time. Application of our model to the SemEval-2015 temporal classification benchmark datasets further reveals that it performs on par with highly optimized task-specific systems.
Anthology ID:
Q16-1003
Volume:
Transactions of the Association for Computational Linguistics, Volume 4
Month:
Year:
2016
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
31–45
Language:
URL:
https://aclanthology.org/Q16-1003
DOI:
10.1162/tacl_a_00081
Bibkey:
Cite (ACL):
Lea Frermann and Mirella Lapata. 2016. A Bayesian Model of Diachronic Meaning Change. Transactions of the Association for Computational Linguistics, 4:31–45.
Cite (Informal):
A Bayesian Model of Diachronic Meaning Change (Frermann & Lapata, TACL 2016)
Copy Citation:
PDF:
https://aclanthology.org/Q16-1003.pdf