1
Your word
measured
“he blocked the way out”
Definitions come from WordNet, a hand-curated dictionary.
an opening that permits escape or release
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“he blocked the way out”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
enter is the dictionary opposite of exits, yet this model puts it closer than 13 of the 15 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 exits, 1 of 8 also appear in the dictionary. 15 of 30 dictionary synonyms are in this build; the rest have no vector to compare yet.
enter is the dictionary opposite of exits, yet this model puts it closer than 14 of the 15 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 exits, 1 of 8 also appear in the dictionary. 15 of 30 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits exits 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.
enter is the dictionary opposite of exits, yet this model puts it closer than 8 of the 15 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 exits. 15 of 30 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.
This model splits exits 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.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to exits. 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 exits. That gap is the model’s own learned association.
This model splits exits 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 exits. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.