Temporal Analysis of Language through Neural Language Models
Computation and Language
2014-08-26 v1
Abstract
We provide a method for automatically detecting change in language across time through a chronologically trained neural language model. We train the model on the Google Books Ngram corpus to obtain word vector representations specific to each year, and identify words that have changed significantly from 1900 to 2009. The model identifies words such as "cell" and "gay" as having changed during that time period. The model simultaneously identifies the specific years during which such words underwent change.
Keywords
Cite
@article{arxiv.1405.3515,
title = {Temporal Analysis of Language through Neural Language Models},
author = {Yoon Kim and Yi-I Chiu and Kentaro Hanaki and Darshan Hegde and Slav Petrov},
journal= {arXiv preprint arXiv:1405.3515},
year = {2014}
}