Structural Correspondence Learning for Cross-lingual Sentiment Classification with One-to-many Mappings
THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, pp. 3490-3496, 2017.
Structural correspondence learning (SCL) is an effective method for cross-lingual sentiment classification. This approach uses unlabeled documents along with a word translation oracle to automatically induce task specific, cross-lingual correspondences. It transfers knowledge through identifying important features, i.e., pivot features. F...More
PPT (Upload PPT)