Compositional Semantic Parsing across Graphbanks

@inproceedings{Lindemann2019CompositionalSP,
  title={Compositional Semantic Parsing across Graphbanks},
  author={Matthias Lindemann and Jonas Groschwitz and Alexander Koller},
  booktitle={ACL},
  year={2019}
}
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. 

Citations

Publications citing this paper.
SHOWING 1-3 OF 3 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

Open SDP 1.2. LINDAT/CLARIN digital library at the Institute of Formal and Applied Linguistics (ÚFAL)

Dan Flickinger, Jan Hajič, +4 authors Daniel Zeman
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

UD Since UD POS tags are different from the English PTB tagset, we use CoreNLP to tag the UD treebanks

We use EDM in an implementation by Buys, Blunsom
  • We use the English treebanks EWT,
  • 2017
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Methods for taking semantic graphs apart and putting them back together again

Jonas Groschwitz
  • Ph.D. thesis,
  • 2019
VIEW 2 EXCERPTS

2018) in using the Chu-Liu-Edmonds algorithm instead of Eisner’s

Groschwitz
  • 2018