1
Your word
measured
“a section of a fishing rod”
Definitions come from WordNet, a hand-curated dictionary.
one of several parts or pieces that fit with others to constitute a whole object
segment is French for segment, 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.
“a section of a fishing rod”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits segment itself, not segment — 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 segment.
Shade shows how close the model puts each word to segment, 1 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to segment, 1 of 8 also appear in the dictionary.
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 segment. 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 segment. 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 segment. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.