Broad-Coverage Semantic Parsing as Transduction release_rp667nswgjcaxiu2uz2a5sh7oa

by Sheng Zhang and Xutai Ma and Kevin Duh and Benjamin Van Durme

Released as a article .

2019  

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-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.
In text/plain format

Archived Files and Locations

application/pdf  524.3 kB
file_qgpsya472bgpzmxsj3nsvwuytm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-09-05
Version   v1
Language   en ?
arXiv  1909.02607v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5ead107d-45e1-44e5-8f16-80e11b5e44d1
API URL: JSON