1
Your word
measured
“they died in the defense of Stalingrad”
Definitions come from WordNet, a hand-curated dictionary.
(military) military action or resources protecting a country against potential enemies
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“they died in the defense of Stalingrad”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
offence is the dictionary opposite of defenses, yet this model puts it closer than 2 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 defenses, 2 of 8 also appear in the dictionary. 5 of 22 dictionary synonyms are in this build; the rest have no vector to compare yet.
offense is the dictionary opposite of defenses, yet this model puts it closer than 2 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 defenses, 2 of 8 also appear in the dictionary. 5 of 22 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits defenses 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.
offense is the dictionary opposite of defenses, 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 defenses. 5 of 22 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 defenses 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 defenses. 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 defenses. That gap is the model’s own learned association.
This model splits defenses 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 defenses. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.