Figure 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Learning curve of the contrastive loss functions. The total loss in the first figure refers to the summation Loss rel + Loss obj .
Source publication
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast, humans learn language by grounding concepts in perception and action and the brain encodes grounded semantics...
