Abstract
The ability to consolidate information of different types is at the core of intelligence, and has tremendous practical value in allowing learning for one task to benefit from generalizations learned for others. In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks. We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks. Despite notable conceptual, formal and domain differences, we show that multitask learning significantly improves UCCA parsing in both in-domain and out-of-domain settings.- Anthology ID:
- P18-1035
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 373–385
- Language:
- URL:
- https://aclanthology.org/P18-1035
- DOI:
- 10.18653/v1/P18-1035
- Cite (ACL):
- Daniel Hershcovich, Omri Abend, and Ari Rappoport. 2018. Multitask Parsing Across Semantic Representations. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 373–385, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Multitask Parsing Across Semantic Representations (Hershcovich et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/bionlp-24-ingestion/P18-1035.pdf
- Code
- danielhers/tupa
- Data
- Universal Dependencies