1
Your word
measured
“I reject the idea of starting a war”
Definitions come from WordNet, a hand-curated dictionary.
refuse to accept or acknowledge
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“I reject the idea of starting a war”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
accept is the dictionary opposite of rejecting, yet this model puts it closer than 4 of the 5 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 rejecting, 1 of 8 also appear in the dictionary. 5 of 16 dictionary synonyms are in this build; the rest have no vector to compare yet.
accept is the dictionary opposite of rejecting, yet this model puts it closer than 3 of the 5 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 rejecting, 1 of 8 also appear in the dictionary. 5 of 16 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits rejecting into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
accept is the dictionary opposite of rejecting, yet this model puts it closer than 3 of the 5 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 rejecting, 1 of 8 also appear in the dictionary. 5 of 16 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.
This model splits rejecting into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
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 rejecting. 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 rejecting. That gap is the model’s own learned association.
This model splits rejecting into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to rejecting. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.