A multi-view hierarchical attention model with multiple instance learning predicts movie story tags from synopses plus reviews, and its attention scores extract open-vocabulary tags from reviews without direct supervision.
In Proceedings of the ECML/PKDD 2008 Discovery Challenge
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
-
Multi-view Story Characterization from Movie Plot Synopses and Reviews
A multi-view hierarchical attention model with multiple instance learning predicts movie story tags from synopses plus reviews, and its attention scores extract open-vocabulary tags from reviews without direct supervision.