1
Your word
measured
“the gun in his pocket made an obvious bulge”
Definitions come from WordNet, a hand-curated dictionary.
something that bulges out or is protuberant or projects from its surroundings
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the gun in his pocket made an obvious bulge”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits humps 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 humps. 10 of 39 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits humps 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 humps. 10 of 39 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits humps 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 humps. 10 of 39 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 humps 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.
This model splits humps 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.
This model splits humps 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.
This model splits humps 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 humps. That gap is the model’s own learned association.
This model splits humps 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 humps. That gap is the model’s own learned association.
This model splits humps 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 humps. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.