English Abstractness / Concreteness Ratings
Maximilian Köper & Sabine Schulte im Walde
We created a new collection of English concreteness / abstractness norms for 3 million English words and Multiword expression. We relied on the google pretrained vectors from word2vec which are available here: GoogleNews-vectors-negative300.
The neural network implementation used in our experiements is based on this implementation.
Some (random) example words:
- razor_blade 9.651
- Oreo_cookies 9.392
- toilet_paper 9.002
- chocolate 9.171
- pizza 9.013
- ideals 0.083
- endlessly 0.075
- irresponsibly 0.058
Maximilian Köper, Sabine Schulte im Walde (2017)
Improving Verb Metaphor Detection by Propagating Abstractness to Words, Phrases and Individual Senses
In: Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications (SENSE). Valencia, Spain.