Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-36125 | Title: | Compositional Semantic Parsing across Graphbanks |
| Author(s): | Lindemann, Matthias Groschwitz, Jonas Koller, Alexander |
| Editor(s): | Nakov, Preslav Palmer, Alexis |
| Language: | English |
| Title: | The 57th Annual Meeting of the Association for Computational Linguistics - tutorial abstracts : July 28, 2019, Florene, Italy : ACL 2019 |
| Startpage: | 4576 |
| Endpage: | 4585 |
| Publisher/Platform: | Association for Computational Linguistics |
| Year of Publication: | 2019 |
| Title of the Conference: | ACL 2019 |
| Place of the conference: | Florence, Italy |
| Publikation type: | Conference Paper |
| 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. |
| DOI of the first publication: | 10.18653/v1/P19-1450 |
| URL of the first publication: | https://aclanthology.org/P19-1450.pdf |
| Link to this record: | hdl:20.500.11880/32899 http://dx.doi.org/10.22028/D291-36125 |
| ISBN: | 978-1-950737-50-5 |
| Date of registration: | 10-May-2022 |
| Faculty: | P - Philosophische Fakultät |
| Department: | P - Sprachwissenschaft und Sprachtechnologie |
| Professorship: | P - Prof. Dr. Alexander Koller |
| Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.