1
Your word
measured
“floppy disks are noted for their relatively slow speed and small capacity and low price”
Definitions come from WordNet, a hand-curated dictionary.
a small plastic magnetic disk enclosed in a stiff envelope with a radial slit; used to store data or programs for a microcomputer
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“floppy disks are noted for their relatively slow speed and small capacity and low price”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to floppy. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits floppy 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 floppy. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits floppy 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 floppy. 0 of 2 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 floppy 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 floppy 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.
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 floppy. That gap is the model’s own learned association.
This model splits floppy 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 floppy. That gap is the model’s own learned association.
This model splits floppy 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 floppy. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.