Definitions come from WordNet, a hand-curated dictionary.
an inflammatory disease of connective tissue with variable features including fever and weakness and fatigability and joint pains and skin lesions on the face or neck or arms
sle is Japanese for sle, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Japanese headword, not a Japanese definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This panel splits sle itself, not sle — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to sle. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to sle. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to sle. 0 of 2 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 sle. 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 sle. 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 sle. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.