1
Your word
measured
“a screen of trees afforded privacy”
Definitions come from WordNet, a hand-curated dictionary.
a covering that serves to conceal or shelter something
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“a screen of trees afforded privacy”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
uncover is the dictionary opposite of cover, yet this model puts it closer than 18 of the 27 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 cover, 1 of 8 also appear in the dictionary. 27 of 50 dictionary synonyms are in this build; the rest have no vector to compare yet.
uncover is the dictionary opposite of cover, yet this model puts it closer than 23 of the 27 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 cover, 1 of 8 also appear in the dictionary. 27 of 50 dictionary synonyms are in this build; the rest have no vector to compare yet.
uncover is the dictionary opposite of cover, yet this model puts it closer than 26 of the 27 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 cover, 1 of 8 also appear in the dictionary. 27 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 cover. 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 cover. 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 cover. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.