1
Your word
measured
“a desirable job”
Definitions come from WordNet, a hand-curated dictionary.
worth having or seeking or achieving
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“a desirable job”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
undesirable is the dictionary opposite of desirable, yet this model puts it closer than every one of the 2 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 desirable, 1 of 8 also appear in the dictionary.
undesirable is the dictionary opposite of desirable, yet this model puts it closer than every one of the 2 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 desirable.
This model splits desirable 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.
undesirable is the dictionary opposite of desirable, yet this model puts it closer than every one of the 2 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 desirable.
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 desirable 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 desirable. 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 desirable. That gap is the model’s own learned association.
This model splits desirable 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 desirable. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.