1
Your word
measured
“before it was known that they were the same object the evening star was called Venus and the morning star was called Lucifer”
Definitions come from WordNet, a hand-curated dictionary.
the second nearest planet to the sun; it is peculiar in that its rotation is slow and retrograde (in the opposite sense of the Earth and all other planets except Uranus); it is visible from Earth as an early `morning star' or an `evening star'
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“before it was known that they were the same object the evening star was called Venus and the morning star was called Lucifer”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits venus 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 venus. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits venus 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 venus. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits venus 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 venus. 0 of 2 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 venus 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 venus 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 venus 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 venus 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 venus. That gap is the model’s own learned association.
This model splits venus 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 venus. That gap is the model’s own learned association.
This model splits venus 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 venus. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.