Broad-Coverage Semantic Parsing as Transduction
This work addresses the challenge of semantic parsing for natural language processing researchers, offering a unified approach that is incremental in nature.
The authors tackled the problem of unifying broad-coverage semantic parsing tasks under a transduction paradigm, proposing an attention-based neural framework that incrementally builds meaning representations, resulting in state-of-the-art improvements on AMR and UCCA tasks and competitive performance on SDP.
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-trained aligner. Experiments conducted on three separate broad-coverage semantic parsing tasks -- AMR, SDP and UCCA -- demonstrate that our attention-based neural transducer improves the state of the art on both AMR and UCCA, and is competitive with the state of the art on SDP.