@inproceedings{CharbonnierWartena2020, author = {Jean Charbonnier and Christian Wartena}, title = {Predicting the Concreteness of German Words}, series = {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 and Don Tuggener and Manuela H{\"u}rlimann and Mark Cieliebak and Martin Volk}, issn = {1613-0073}, doi = {10.25968/opus-2075}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:960-opus4-20753}, year = {2020}, abstract = {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.}, language = {en} }