@article{frermann-lapata-2016-bayesian,
title = "A {B}ayesian Model of Diachronic Meaning Change",
author = "Frermann, Lea and
Lapata, Mirella",
journal = "Transactions of the Association for Computational Linguistics",
volume = "4",
year = "2016",
url = "https://www.aclweb.org/anthology/Q16-1003",
doi = "10.1162/tacl_a_00081",
pages = "31--45",
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.",
}
1. What is it?
They propose a dynamic bayesian model.
2. What is amazing compared to previous works?
3. Where is the key to technologies and techniques?
SCAN, dynamic bayesian model for Semantic ChANge
Looks like dynamic topic model.
4. How did evaluate it?
4.1 Modeling meaning change of words (band, power, transport, bank)
Their model can track
band: musical band is increasing since 1812.
power: new sense, power as supply of energy is born in mid-19th (below)
5. Is there a discussion?
In contrast, their model(trained COHA + DTE + CLMET3.0) was worse than PMI(trained Google Books Ngram).
a1da4
commented
4 years ago
0. Paper
@article{frermann-lapata-2016-bayesian, title = "A {B}ayesian Model of Diachronic Meaning Change", author = "Frermann, Lea and Lapata, Mirella", journal = "Transactions of the Association for Computational Linguistics", volume = "4", year = "2016", url = "https://www.aclweb.org/anthology/Q16-1003", doi = "10.1162/tacl_a_00081", pages = "31--45", 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.", }
1. What is it?
They propose a dynamic bayesian model.
2. What is amazing compared to previous works?
3. Where is the key to technologies and techniques?
SCAN, dynamic bayesian model for Semantic ChANge
Looks like dynamic topic model.
4. How did evaluate it?
4.1 Modeling meaning change of words (band, power, transport, bank)
Their model can track
5. Is there a discussion?
In contrast, their model(trained COHA + DTE + CLMET3.0) was worse than PMI(trained Google Books Ngram).
6. Which paper should read next?