Volltext-Downloads (blau) und Frontdoor-Views (grau)

Predicting the Concreteness of German Words

  • Concreteness of words has been measured and used in psycholinguistics already for decades. Recently, it is also used in retrieval and NLP tasks. For English a number of well known datasets has been established with average values for perceived concreteness. We give an overview of available datasets for German, their correlation and evaluate prediction algorithms for concreteness of German words. We show that these algorithms achieve similar results as for English datasets. Moreover, we show for all datasets there are no significant differences between a prediction model based on a regression model using word embeddings as features and a prediction algorithm based on word similarity according to the same embeddings.

Download full text files

Export metadata


Author:Jean CharbonnierORCiD, Christian WartenaORCiDGND
Parent Title (English):SWISSTEXT & KONVENS 2020 : Swiss Text Analytics Conference & Conference on Natural Language Processing 2020; Proceedings of the 5th Swiss Text Analytics Conference (SwissText) & 16th Conference on Natural Language Processing (KONVENS), CEUR Workshop Proceedings Vol. 2624
Editor:Sarah Ebling, Don Tuggener, Manuela H├╝rlimann, Mark Cieliebak, Martin Volk
Document Type:Conference Proceeding
Year of Completion:2020
Publishing Institution:Hochschule Hannover
Release Date:2021/09/14
Tag:Concreteness; Semantics; Word Norms
GND Keyword:Konkretum <Linguistik>; Semantik; Sprachnorm
Page Number:6
Link to catalogue:177579976X
Institutes:Fakult├Ąt III - Medien, Information und Design
DDC classes:400 Sprache, Linguistik
020 Bibliotheks- und Informationswissenschaften
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International