1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
a Hebrew prophet in the Old Testament who opposed the worship of idols; he was persecuted for rebuking Ahab and Jezebel (king and queen of Israel); he was taken up to heaven in a chariot of fire (circa 9th century BC)
Élie is French for elijah, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the French headword, not a French 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 Élie itself, not elijah — 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.
This model splits elijah into 3 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
WordNet lists none for this word.
Shade shows how close the model puts each word to elijah.
This model splits elijah 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.
WordNet lists none for this word.
Shade shows how close the model puts each word to elijah.
This model splits elijah into 3 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
WordNet lists none for this word.
Shade shows how close the model puts each word to elijah.
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 elijah into 3 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
This model splits elijah 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.
This model splits elijah into 3 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.
This model splits elijah into 3 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 elijah. That gap is the model’s own learned association.
This model splits elijah 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 elijah. That gap is the model’s own learned association.
This model splits elijah into 3 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 elijah. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.