1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
a return on a shot that seemed impossible to reach and would normally have resulted in a point for the opponent
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
end is the dictionary opposite of get, yet this model puts it closer than 19 of the 44 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 get, 2 of 8 also appear in the dictionary. 44 of 69 dictionary synonyms are in this build; the rest have no vector to compare yet.
end is the dictionary opposite of get, yet this model puts it closer than 38 of the 44 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 get, 2 of 8 also appear in the dictionary. 44 of 69 dictionary synonyms are in this build; the rest have no vector to compare yet.
leave is the dictionary opposite of get, yet this model puts it closer than 29 of the 44 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 get, 1 of 8 also appear in the dictionary. 44 of 69 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 get. 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 get. 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 get. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.