1
Your word
measured
“they built it right over a geological fault”
Definitions come from WordNet, a hand-curated dictionary.
(geology) a crack in the earth's crust resulting from the displacement of one side with respect to the other
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“they built it right over a geological fault”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits faulting 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 faulting, 1 of 8 also appear in the dictionary. 5 of 6 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits faulting 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 faulting, 1 of 8 also appear in the dictionary. 5 of 6 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits faulting 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 faulting, 1 of 8 also appear in the dictionary. 5 of 6 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 faulting 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 faulting 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 faulting 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 faulting 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 faulting. That gap is the model’s own learned association.
This model splits faulting 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 faulting. That gap is the model’s own learned association.
This model splits faulting 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 faulting. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.