1
Your word
measured
“containment of communist expansion was a central principle of United States' foreign policy from 1947 to the 1975”
Definitions come from WordNet, a hand-curated dictionary.
a policy of creating strategic alliances in order to check the expansion of a hostile power or ideology or to force it to negotiate peacefully
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“containment of communist expansion was a central principle of United States' foreign policy from 1947 to the 1975”
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 containment.
WordNet lists none for this word.
Shade shows how close the model puts each word to containment.
This model splits containment 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 containment.
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 containment 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 containment. 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 containment. That gap is the model’s own learned association.
This model splits containment 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 containment. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.