1
Your word
measured
“I am accumulating evidence for the man's unfaithfulness to his wife”
Definitions come from WordNet, a hand-curated dictionary.
get or gather together
acumular is Spanish for collected, 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.
“I am accumulating evidence for the man's unfaithfulness to his wife”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits acumular itself, not collected — 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.
spread is the dictionary opposite of collected, yet this model puts it closer than 4 of the 7 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 collected, 2 of 8 also appear in the dictionary. 7 of 21 dictionary synonyms are in this build; the rest have no vector to compare yet.
spread is the dictionary opposite of collected, yet this model puts it closer than 3 of the 7 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 collected, 2 of 8 also appear in the dictionary. 7 of 21 dictionary synonyms are in this build; the rest have no vector to compare yet.
spread is the dictionary opposite of collected, yet this model puts it closer than 1 of the 7 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 collected, 2 of 8 also appear in the dictionary. 7 of 21 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 collected. 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 collected. 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 collected. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.