Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-10462
For citation please use:
Main Title: Times Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddings
Author(s): Brandl, Stephanie
Lassner, David
Type: Conference Object
Language Code: en
Abstract: We propose Word Embedding Networks, a novel method that is able to learn word embeddings of individual data slices while simultaneously aligning and ordering them without feeding temporal information a priori to the model. This gives us the opportunity to analyse the dynamics in word embeddings on a large scale in a purely data-driven manner. In experiments on two different newspaper corpora, the New York Times (English) and die Zeit (German), we were able to show that time actually determines the dynamics of semantic change. However, there is by no means a uniform evolution, but instead times of faster and times of slower change.
URI: https://depositonce.tu-berlin.de/handle/11303/11575
http://dx.doi.org/10.14279/depositonce-10462
Issue Date: 2-Aug-2019
Date Available: 17-Aug-2020
DDC Class: 004 Datenverarbeitung; Informatik
410 Linguistik
Subject(s): word embeddings
word embedding networks
WEN
machine learning
text corpora
semantic change
Sponsor/Funder: BMBF, 01IS17058, MALT3 - MAschinelles Lernen-The Tricks of the Trade
License: https://creativecommons.org/licenses/by/4.0/
Proceedings Title: Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change
Publisher: Association for Computational Linguistics
Publisher Place: Stroudsburg, PA
Publisher DOI: 10.18653/v1/W19-4718
Page Start: 146
Page End: 150
ISBN: 978-1-950737-31-4
Appears in Collections:FG Maschinelles Lernen » Publications

Files in This Item:
brandl_lassner_2019.pdf
Format: Adobe PDF | Size: 330.24 kB
DownloadShow Preview
Thumbnail

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons