1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
a Stuart king of Scotland who married a daughter of Henry VII; when England and France went to war in 1513 he invaded England and died in defeat at Flodden (1473-1513)
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
free is the dictionary opposite of james, yet this model puts it closer than 3 of the 7 synonyms 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 james. 7 of 31 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits james 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.
free is the dictionary opposite of james, yet this model puts it closer than 3 of the 7 synonyms 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 james. 7 of 31 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits james 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 james. 7 of 31 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 james 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 james 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.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to james. That gap is the model’s own learned association.
This model splits james 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 james. That gap is the model’s own learned association.
This model splits james 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 james. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.