1
Your word
measured
“You cannot windsurf when the air is completely still”
Definitions come from WordNet, a hand-curated dictionary.
ride standing on a surfboard with an attached sail, on water
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“You cannot windsurf when the air is completely still”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits windsurfing into 3 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 windsurfing. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits windsurfing into 4 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 windsurfing. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits windsurfing into 4 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 windsurfing. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
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 windsurfing into 3 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 windsurfing into 4 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 windsurfing into 4 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 windsurfing into 3 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 windsurfing. That gap is the model’s own learned association.
This model splits windsurfing into 4 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 windsurfing. That gap is the model’s own learned association.
This model splits windsurfing into 4 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 windsurfing. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.