1
Your word
measured
“the Tamil Tigers perfected suicide bombing as a weapon of war”
Definitions come from WordNet, a hand-curated dictionary.
a terrorist organization in Sri Lanka that began in 1970 as a student protest over the limited university access for Tamil students; currently seeks to establish an independent Tamil state called Eelam; relies on guerilla strategy including terrorist tactics that target key government and military personnel
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the Tamil Tigers perfected suicide bombing as a weapon of war”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits tigers 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 tigers. 1 of 7 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to tigers, 1 of 8 also appear in the dictionary. 1 of 7 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits tigers into 3 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 tigers. 1 of 7 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 tigers 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 tigers into 3 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 tigers 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 tigers. 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 tigers. That gap is the model’s own learned association.
This model splits tigers into 3 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 tigers. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.