1
Your word
measured
“an attempt to refine the existent machinery to make it more efficient”
Definitions come from WordNet, a hand-curated dictionary.
having existence or being or actuality
existant is French for existent, 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.
“an attempt to refine the existent machinery to make it more efficient”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits existant itself, not existent — 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.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
potential is the dictionary opposite of existent, yet this model puts it closer than 2 of the 3 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 existent.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to existent.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
unreal is the dictionary opposite of existent, yet this model puts it closer than 2 of the 3 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 existent.
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.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to existent. That gap is the model’s own learned association.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to existent. That gap is the model’s own learned association.
This model splits existent into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to existent. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.