Universal Decompositional Semantic Parsing
This work addresses semantic parsing for natural language processing researchers, but it is incremental as it builds on existing UDS frameworks with a new model.
The authors tackled the problem of parsing natural language into Universal Decompositional Semantics (UDS) representations by introducing a transductive model that jointly learns to map utterances into graph structures and annotate them with semantic attribute scores, achieving comparable performance to a strong pipeline model while also predicting attributes.
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 into the UDS graph structure, and show that our transductive parser performs comparably while additionally performing attribute prediction. By analyzing the attribute prediction errors, we find the model captures natural relationships between attribute groups.