An autoregressive 'sequence' model fed with per-label probability scores improves constrained multi-label classification on most tested datasets and learns logical constraints directly from the data.
In: Workshop on challenges in representation learning (2013)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Constraint-aware Learning of Probabilistic Sequential Models for Multi-Label Classification
An autoregressive 'sequence' model fed with per-label probability scores improves constrained multi-label classification on most tested datasets and learns logical constraints directly from the data.