1
Your word
measured
“The dress remained wet after repeated attempts to dry it”
Definitions come from WordNet, a hand-curated dictionary.
stay the same; remain in a certain state
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“The dress remained wet after repeated attempts to dry it”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
depart is the dictionary opposite of stayed, yet this model puts it closer than 3 of the 8 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 stayed, 1 of 8 also appear in the dictionary. 8 of 18 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to stayed, 2 of 8 also appear in the dictionary. 8 of 18 dictionary synonyms are in this build; the rest have no vector to compare yet.
depart is the dictionary opposite of stayed, yet this model puts it closer than 3 of the 8 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 stayed, 1 of 8 also appear in the dictionary. 8 of 18 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 stayed. 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 stayed. 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 stayed. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.