1
Your word
measured
“the scientist corresponds with colleagues in order to learn about matters relevant to her own research”
Definitions come from WordNet, a hand-curated dictionary.
having a bearing on or connection with the subject at issue
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the scientist corresponds with colleagues in order to learn about matters relevant to her own research”
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 relevant.
WordNet lists none for this word.
Shade shows how close the model puts each word to relevant.
WordNet lists none for this word.
Shade shows how close the model puts each word to relevant.
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 relevant. 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 relevant. 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 relevant. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.