Thumbnail Image
🆕 Date Issued:
2019-08-02
🗄 In DepositOnce:2020-08-17
Published Version

Please use this identifier to cite or link to this item:

Times Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddings

Brandl, Stephanie; Lassner, David

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.
word embeddingsword embedding networksWENmachine learningtext corporasemantic change
Published in: Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, 10.18653/v1/W19-4718, Association for Computational Linguistics
Creative Commons Attribution 4.0 (CC BY)Creative Commons Attribution 4.0 (CC BY)
Full item page