1
Your word
measured
“in the fall of 1973”
Definitions come from WordNet, a hand-curated dictionary.
the season when the leaves fall from the trees
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“in the fall of 1973”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
rise is the dictionary opposite of fall, yet this model puts it closer than 22 of the 25 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 fall. 25 of 43 dictionary synonyms are in this build; the rest have no vector to compare yet.
rise is the dictionary opposite of fall, yet this model puts it closer than 24 of the 25 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 fall, 1 of 8 also appear in the dictionary. 25 of 43 dictionary synonyms are in this build; the rest have no vector to compare yet.
rise is the dictionary opposite of fall, yet this model puts it closer than 23 of the 25 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 fall, 2 of 8 also appear in the dictionary. 25 of 43 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 fall. 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 fall. 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 fall. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.