1
Your word
measured
“This nest egg will ensure a nice retirement for us”
Definitions come from WordNet, a hand-curated dictionary.
make certain of
保证 is Chinese for ensure, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Chinese headword, not a Chinese definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“This nest egg will ensure a nice retirement for us”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits 保证 itself, not ensure — 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 ensure. 8 of 9 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to ensure, 3 of 8 also appear in the dictionary. 8 of 9 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to ensure, 2 of 8 also appear in the dictionary. 8 of 9 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 ensure. 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 ensure. 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 ensure. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.