1
Your word
measured
“I waited several days for his answer”
Definitions come from WordNet, a hand-curated dictionary.
a statement (either spoken or written) that is made to reply to a question or request or criticism or accusation
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“I waited several days for his answer”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
question is the dictionary opposite of answer, yet this model puts it closer than 9 of the 10 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 answer, 2 of 8 also appear in the dictionary. 10 of 11 dictionary synonyms are in this build; the rest have no vector to compare yet.
question is the dictionary opposite of answer, yet this model puts it closer than 8 of the 10 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 answer, 4 of 8 also appear in the dictionary. 10 of 11 dictionary synonyms are in this build; the rest have no vector to compare yet.
question is the dictionary opposite of answer, yet this model puts it closer than 8 of the 10 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 answer, 3 of 8 also appear in the dictionary. 10 of 11 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 answer. 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 answer. 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 answer. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.