Transductive Parsing for Universal Decompositional Semantics
share
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores. We also introduce a strong pipeline model for parsing UDS graph structure, and show that our parser can perform comparably while additionally performing attribute prediction.
READ FULL TEXT