1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
a city in southeastern Arizona ringed by mountain ranges; long known as a winter and health resort but the population shift from industrial states to the Sunbelt resulted in rapid growth late in the 20th century
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits tucson 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 tucson.
This model splits tucson 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.
WordNet lists none for this word.
Shade shows how close the model puts each word to tucson.
This model splits tucson 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.
WordNet lists none for this word.
Shade shows how close the model puts each word to tucson.
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 tucson 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 tucson 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.
This model splits tucson 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 tucson 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 tucson. That gap is the model’s own learned association.
This model splits tucson 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 tucson. That gap is the model’s own learned association.
This model splits tucson 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 tucson. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.