1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
a gambling card game in which chips are placed on the ace and king and queen and jack of separate suits (taken from a separate deck); a player plays the lowest card of a suit in his hand and successively higher cards are played until the sequence stops; the player who plays a card matching one in the layout wins all the chips on that card
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.
start is the dictionary opposite of stops, yet this model puts it closer than 23 of the 24 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 stops, 1 of 8 also appear in the dictionary. 24 of 50 dictionary synonyms are in this build; the rest have no vector to compare yet.
start is the dictionary opposite of stops, yet this model puts it closer than 23 of the 24 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 stops, 2 of 8 also appear in the dictionary. 24 of 50 dictionary synonyms are in this build; the rest have no vector to compare yet.
start is the dictionary opposite of stops, yet this model puts it closer than 23 of the 24 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 stops, 1 of 8 also appear in the dictionary. 24 of 50 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.
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 stops. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to stops. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to stops. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.