1
Your word
measured
“the telephone is an annoying interruption”
Definitions come from WordNet, a hand-curated dictionary.
some abrupt occurrence that interrupts an ongoing activity
interruption is French for break, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the French headword, not a French definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the telephone is an annoying interruption”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits interruption itself, not break — 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.
make is the dictionary opposite of break, yet this model puts it closer than 39 of the 41 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 break, 1 of 8 also appear in the dictionary. 41 of 99 dictionary synonyms are in this build; the rest have no vector to compare yet.
make is the dictionary opposite of break, yet this model puts it closer than 40 of the 41 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 break, 2 of 8 also appear in the dictionary. 41 of 99 dictionary synonyms are in this build; the rest have no vector to compare yet.
make is the dictionary opposite of break, yet this model puts it closer than 32 of the 41 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 break, 2 of 8 also appear in the dictionary. 41 of 99 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 break. 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 break. 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 break. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.