1
Your word
measured
“a just and lasting peace”
Definitions come from WordNet, a hand-curated dictionary.
used especially of what is legally or ethically right or proper or fitting; - A.Lincoln
justo is Spanish for just, 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.
“a just and lasting peace”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits justo itself, not just — 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.
unfair is the dictionary opposite of just, yet this model puts it closer than 4 of the 14 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 just, 4 of 8 also appear in the dictionary. 14 of 15 dictionary synonyms are in this build; the rest have no vector to compare yet.
unfair is the dictionary opposite of just, yet this model puts it closer than 2 of the 14 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 just, 1 of 8 also appear in the dictionary. 14 of 15 dictionary synonyms are in this build; the rest have no vector to compare yet.
unfair is the dictionary opposite of just, yet this model puts it closer than 2 of the 14 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 just, 3 of 8 also appear in the dictionary. 14 of 15 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 just. 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 just. 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 just. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.