Anchors in Embedding Space: A Simple Concept Tracking Approach to Support Conceptual History Research

Jetske Adams, Martha Larson, Jaap Verheul, Michael Boyden


Abstract
We introduce a simple concept tracking approach to support conceptual history research. Building on the existing practices of conceptual historians, we use dictionaries to identify “anchors”, which represent primary dimensions of meaning of a concept. Then, we create a plot showing how a key concept has evolved over time in a historical corpus in relation to these dimensions. We demonstrate the approach by plotting the change of several key concepts in the COHA corpus.
Anthology ID:
2023.lchange-1.9
Volume:
Proceedings of the 4th Workshop on Computational Approaches to Historical Language Change
Month:
December
Year:
2023
Address:
Singapore
Editors:
Nina Tahmasebi, Syrielle Montariol, Haim Dubossarsky, Andrey Kutuzov, Simon Hengchen, David Alfter, Francesco Periti, Pierluigi Cassotti
Venue:
LChange
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
87–92
Language:
URL:
https://aclanthology.org/2023.lchange-1.9
DOI:
10.18653/v1/2023.lchange-1.9
Bibkey:
Cite (ACL):
Jetske Adams, Martha Larson, Jaap Verheul, and Michael Boyden. 2023. Anchors in Embedding Space: A Simple Concept Tracking Approach to Support Conceptual History Research. In Proceedings of the 4th Workshop on Computational Approaches to Historical Language Change, pages 87–92, Singapore. Association for Computational Linguistics.
Cite (Informal):
Anchors in Embedding Space: A Simple Concept Tracking Approach to Support Conceptual History Research (Adams et al., LChange 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.lchange-1.9.pdf