Help Privacy Policy Disclaimer
  Advanced SearchBrowse




Conference Paper

Seeing the advantage: Visually grounding word embeddings to better capture human semantic knowledge


Merkx,  Danny
Center for Language Studies, External Organizations;
International Max Planck Research School for Language Sciences, MPI for Psycholinguistics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

Merkx_etal_2022_seeing the advantage.pdf
(Publisher version), 282KB

Supplementary Material (public)
There is no public supplementary material available

Merkx, D., Frank, S. L., & Ernestus, M. (2022). Seeing the advantage: Visually grounding word embeddings to better capture human semantic knowledge. In E. Chersoni, N. Hollenstein, C. Jacobs, Y. Oseki, L. Prévot, & E. Santus (Eds.), Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2022) (pp. 1-11). Stroudsburg, PA, USA: Association for Computational Linguistics (ACL).

Cite as: https://hdl.handle.net/21.11116/0000-000B-5D5A-9
Distributional semantic models capture word-level meaning that is useful in many natural language processing tasks and have even been shown to capture cognitive aspects of word meaning. The majority of these models are purely text based, even though the human sensory experience is much richer. In this paper we create visually grounded word embeddings by combining English text and images and compare them to popular text-based methods, to see if visual information allows our model to better capture cognitive aspects of word meaning. Our analysis shows that visually grounded embedding similarities are more predictive of the human reaction times in a large priming experiment than the purely text-based embeddings. The visually grounded embeddings also correlate well with human word similarity ratings.Importantly, in both experiments we show that he grounded embeddings account for a unique portion of explained variance, even when we include text-based embeddings trained on huge corpora. This shows that visual grounding allows our model to capture information that cannot be extracted using text as the only source of information.