1
Your word
measured
“there was an addition to property taxes this year”
Definitions come from WordNet, a hand-curated dictionary.
a quantity that is added
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“there was an addition to property taxes this year”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
loss is the dictionary opposite of gain, yet this model puts it closer than 15 of the 18 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 gain, 3 of 8 also appear in the dictionary. 18 of 27 dictionary synonyms are in this build; the rest have no vector to compare yet.
lose is the dictionary opposite of gain, yet this model puts it closer than every one of the 18 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 gain. 18 of 27 dictionary synonyms are in this build; the rest have no vector to compare yet.
loss is the dictionary opposite of gain, yet this model puts it closer than every one of the 18 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 gain. 18 of 27 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 gain. 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 gain. 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 gain. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.