1
Your word
measured
“an eruptive disease”
Definitions come from WordNet, a hand-curated dictionary.
producing or characterized by eruptions
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“an eruptive disease”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits eruptive 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.
aqueous is the dictionary opposite of eruptive, yet this model puts it closer than every one of the 1 synonym it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to eruptive.
This model splits eruptive 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 eruptive.
This model splits eruptive 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.
aqueous is the dictionary opposite of eruptive, yet this model puts it closer than every one of the 1 synonym it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to eruptive.
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 eruptive 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 eruptive 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 eruptive 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.
This model splits eruptive 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 eruptive. That gap is the model’s own learned association.
This model splits eruptive 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 eruptive. That gap is the model’s own learned association.
This model splits eruptive 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 eruptive. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.