1
Your word
measured
“I donated blood to the Red Cross for the victims of the earthquake”
Definitions come from WordNet, a hand-curated dictionary.
give to a charity or good cause
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“I donated blood to the Red Cross for the victims of the earthquake”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
WordNet lists none for this word.
Shade shows how close the model puts each word to donate.
WordNet lists none for this word.
Shade shows how close the model puts each word to donate.
This model splits donate 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.
WordNet lists none for this word.
Shade shows how close the model puts each word to donate.
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 donate 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 donate. 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 donate. That gap is the model’s own learned association.
This model splits donate 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 donate. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.