Given only category names, CatE learns a discriminative embedding space and a per-word specificity scalar, then retrieves terms that are similar to a category and more specific than its name, beating seeded and unsupervised topic models on category-relevant term retrieval.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Discriminative Topic Mining via Category-Name Guided Text Embedding
Given only category names, CatE learns a discriminative embedding space and a per-word specificity scalar, then retrieves terms that are similar to a category and more specific than its name, beating seeded and unsupervised topic models on category-relevant term retrieval.