A compositional neural semantic parser achieves competitive accuracies across diverse graphbanks for the first time and sets new state-of-the-art results on DM, PAS, PSD, AMR 2015 and EDS when combined with BERT and multi-task learning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compositional Semantic Parsing Across Graphbanks
A compositional neural semantic parser achieves competitive accuracies across diverse graphbanks for the first time and sets new state-of-the-art results on DM, PAS, PSD, AMR 2015 and EDS when combined with BERT and multi-task learning.