ACL LACSS 2014 - Temporal Analysis of Language through Neural Network Language Models

Temporal Analysis of Language through Neural Network Language Models

Yoon Kim

ACL Workshop on Language Technology and Computational Social Science (ACL LACSS 2014)
Baltimore, Maryland, USA, June 26 - 26, 2014

Abstract

We provide a method for automatically detecting change in language across time through a chronologically trained neural network language model. We train the model on the Google Books N-gram 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.

START Conference Manager (V2.61.0 - Rev. 3312)