Abstract
We present a new approach to learning a semantic parser from multiple datasets, even when the target semantic formalisms are drastically different and the underlying corpora do not overlap. We handle such “disjoint” data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly.- Anthology ID:
- N18-1135
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1492–1502
- Language:
- URL:
- https://aclanthology.org/N18-1135
- DOI:
- 10.18653/v1/N18-1135
- Cite (ACL):
- Hao Peng, Sam Thomson, Swabha Swayamdipta, and Noah A. Smith. 2018. Learning Joint Semantic Parsers from Disjoint Data. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1492–1502, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Learning Joint Semantic Parsers from Disjoint Data (Peng et al., NAACL 2018)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/N18-1135.pdf
- Code
- Noahs-ARK/NeurboParser + additional community code
- Data
- FrameNet