1
Your word
measured
“the most desirable feature of the park are the beautiful views”
Definitions come from WordNet, a hand-curated dictionary.
the visual percept of a region
panorama is Spanish for vista, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Spanish headword, not a Spanish definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the most desirable feature of the park are the beautiful views”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits panorama itself, not vista — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to vista.
Shade shows how close the model puts each word to vista, 2 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to vista, 1 of 8 also appear in the dictionary.
Model neighbours are distributional, not dictionary synonyms. Two words can be close because they appear in similar sentences, which is why an antonym can outscore a synonym here.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to vista. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to vista. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to vista. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.