1
Your word
measured
“Antarctica is twice the size of Australia”
Definitions come from WordNet, a hand-curated dictionary.
an extremely cold continent at the south pole almost entirely below the Antarctic Circle; covered by an ice cap up to 13,000 feet deep
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“Antarctica is twice the size of Australia”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits antarctica 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 antarctica. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits antarctica 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 antarctica. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits antarctica 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 antarctica. 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 antarctica 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 antarctica 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 antarctica 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 antarctica 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 antarctica. That gap is the model’s own learned association.
This model splits antarctica 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 antarctica. That gap is the model’s own learned association.
This model splits antarctica 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 antarctica. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.