1
Your word
measured
“Grant won a decisive victory in the battle of Chickamauga”
Definitions come from WordNet, a hand-curated dictionary.
a hostile meeting of opposing military forces in the course of a war
combate is Spanish for battle, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Spanish headword, not a Spanish definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“Grant won a decisive victory in the battle of Chickamauga”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits combate itself, not battle — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to battle, 3 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to battle, 3 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to battle, 3 of 8 also appear in the dictionary.
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 battle. 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 battle. 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 battle. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.