1
Your word
measured
“the orifice into the aorta from the lower left chamber of the heart”
Definitions come from WordNet, a hand-curated dictionary.
an aperture or hole that opens into a bodily cavity
orifice is French for porta, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the French headword, not a French definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the orifice into the aorta from the lower left chamber of the heart”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits orifice itself, not porta — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to porta.
Shade shows how close the model puts each word to porta.
This model splits porta 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.
Shade shows how close the model puts each word to porta.
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 porta 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 porta. 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 porta. That gap is the model’s own learned association.
This model splits porta 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 porta. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.