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.- Anthology ID:
- P19-1450
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4576–4585
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/P19-1450/
- DOI:
- 10.18653/v1/P19-1450
- Cite (ACL):
- Matthias Lindemann, Jonas Groschwitz, and Alexander Koller. 2019. Compositional Semantic Parsing across Graphbanks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4576–4585, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Compositional Semantic Parsing across Graphbanks (Lindemann et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/P19-1450.pdf
- Code
- coli-saar/am-parser