1
Your word
measured
“the experience gave him the advantage over me”
Definitions come from WordNet, a hand-curated dictionary.
the quality of having a superior or more favorable position
superioridad is Spanish for advantage, 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.
“the experience gave him the advantage over me”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits superioridad itself, not advantage — 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.
disadvantage is the dictionary opposite of advantage, yet this model puts it closer than every one of the 2 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to advantage, 1 of 8 also appear in the dictionary.
disadvantage is the dictionary opposite of advantage, yet this model puts it closer than every one of the 2 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to advantage, 1 of 8 also appear in the dictionary.
disadvantage is the dictionary opposite of advantage, yet this model puts it closer than every one of the 2 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to advantage, 1 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 advantage. 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 advantage. 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 advantage. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.