indicating the first or earliest or original
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“`proto' is a combining form in a word like `protolanguage' that refers to the hypothetical ancestor of another language or group of languages”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
WordNet lists none for this word.
Shade shows how close the model puts each word to proto.
WordNet lists none for this word.
Shade shows how close the model puts each word to proto.
WordNet lists none for this word.
Shade shows how close the model puts each word to proto.
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 proto. 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 proto. 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 proto. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.