On the Geometry of Concreteness
- In this paper we investigate how concreteness and abstractness are represented in word embedding spaces. We use data for English and German, and show that concreteness and abstractness can be determined independently and turn out to be completely opposite directions in the embedding space. Various methods can be used to determine the direction of concreteness, always resulting in roughly the same vector. Though concreteness is a central aspect of the meaning of words and can be detected clearly in embedding spaces, it seems not as easy to subtract or add concreteness to words to obtain other words or word senses like e.g. can be done with a semantic property like gender.
Author: | Christian WartenaORCiDGND |
---|---|
URN: | urn:nbn:de:bsz:960-opus4-22996 |
DOI: | https://doi.org/10.25968/opus-2299 |
DOI original: | https://doi.org/10.18653/v1/2022.repl4nlp-1.21 |
Parent Title (English): | Proceedings of the 7th Workshop on Representation Learning for NLP |
Document Type: | Conference Proceeding |
Language: | English |
Year of Completion: | 2022 |
Publishing Institution: | Hochschule Hannover |
Release Date: | 2022/06/20 |
Tag: | abstractness; concreteness; word embedding space |
First Page: | 204 |
Last Page: | 212 |
Link to catalogue: | 1813173877 |
Institutes: | Fakultät III - Medien, Information und Design |
DDC classes: | 004 Informatik |
Licence (German): | Creative Commons - CC BY - Namensnennung 4.0 International |