“the inflected forms of a word can be represented by a stem and a list of inflections to be attached”
Definitions come from WordNet, a hand-curated dictionary.
the phonological or orthographic sound or appearance of a word that can be used to describe or identify something
forme is French for form, 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.
“the inflected forms of a word can be represented by a stem and a list of inflections to be attached”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits forme itself, not form — 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 form, 1 of 8 also appear in the dictionary. 33 of 47 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to form, 1 of 8 also appear in the dictionary. 33 of 47 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to form. 33 of 47 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 form. 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 form. 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 form. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.