Broad-Coverage Semantic Parsing as Transduction

EMNLP/IJCNLP (1), pp. 3784-3796, 2019.

Cited by: 25|Views32
EI

Abstract:

We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectively trained without relying on a pre-t...More

Code:

Data:

Your rating :
0

 

Tags
Comments