Definitions come from WordNet, a hand-curated dictionary.
the chief solid component of mammalian urine; synthesized from ammonia and carbon dioxide and used as fertilizer and in animal feed and in plastics
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits urea into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to urea.
Shade shows how close the model puts each word to urea.
This model splits urea into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to urea.
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.
This model splits urea into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
This model splits urea into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
This model splits urea into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to urea. 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 urea. That gap is the model’s own learned association.
This model splits urea into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to urea. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.