Compositional Semantic Parsing Across Graphbanks
Computation and Language
2019-07-16 v2
Abstract
Most semantic parsers that map sentences to graph-based meaning representations are hand-designed for specific graphbanks. We present a compositional neural semantic parser which achieves, for the first time, competitive accuracies across a diverse range of graphbanks. Incorporating BERT embeddings and multi-task learning improves the accuracy further, setting new states of the art on DM, PAS, PSD, AMR 2015 and EDS.
Cite
@article{arxiv.1906.11746,
title = {Compositional Semantic Parsing Across Graphbanks},
author = {Matthias Lindemann and Jonas Groschwitz and Alexander Koller},
journal= {arXiv preprint arXiv:1906.11746},
year = {2019}
}
Comments
Accepted at ACL 2019