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.- Anthology ID:
- W19-4718
- Volume:
- Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Nina Tahmasebi, Lars Borin, Adam Jatowt, Yang Xu
- Venue:
- LChange
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 146–150
- Language:
- URL:
- https://aclanthology.org/W19-4718
- DOI:
- 10.18653/v1/W19-4718
- Cite (ACL):
- Stephanie Brandl and David Lassner. 2019. Times Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddings. In Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change, pages 146–150, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Times Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddings (Brandl & Lassner, LChange 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/W19-4718.pdf