1
Your word
measured
“the ICC was established in 1887 as the first federal agency”
Definitions come from WordNet, a hand-curated dictionary.
a former independent federal agency that supervised and set rates for carriers that transported goods and people between states; was terminated in 1995
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the ICC was established in 1887 as the first federal agency”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits icc 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.
Shade shows how close the model puts each word to icc. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits icc 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.
Shade shows how close the model puts each word to icc. 0 of 1 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits icc 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.
Shade shows how close the model puts each word to icc. 0 of 1 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.
This model splits icc 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 icc 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 icc 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.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
This model splits icc 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 icc. That gap is the model’s own learned association.
This model splits icc 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 icc. That gap is the model’s own learned association.
This model splits icc 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 icc. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.