1
Your word
measured
“a set of books”
Definitions come from WordNet, a hand-curated dictionary.
a group of things of the same kind that belong together and are so used
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“a set of books”
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 set, yet this model puts it closer than 12 of the 36 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 set, 2 of 8 also appear in the dictionary. 36 of 59 dictionary synonyms are in this build; the rest have no vector to compare yet.
rise is the dictionary opposite of set, yet this model puts it closer than 27 of the 36 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 set. 36 of 59 dictionary synonyms are in this build; the rest have no vector to compare yet.
rise is the dictionary opposite of set, yet this model puts it closer than 11 of the 36 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 set. 36 of 59 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 set. 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 set. 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 set. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.