1
Your word
measured
“Call the outcome of an election”
Definitions come from WordNet, a hand-curated dictionary.
make a prediction about; tell in advance
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“Call the outcome of an election”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to predict. 4 of 16 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to predict, 2 of 8 also appear in the dictionary. 4 of 16 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to predict. 4 of 16 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.
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 predict. 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 predict. 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 predict. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.