Universal Decompositional Semantic Parsing

Elias Stengel-Eskin, Aaron Steven White, Sheng Zhang, Benjamin Van Durme


Abstract
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores. We also introduce a strong pipeline model for parsing into the UDS graph structure, and show that our transductive parser performs comparably while additionally performing attribute prediction. By analyzing the attribute prediction errors, we find the model captures natural relationships between attribute groups.
Anthology ID:
2020.acl-main.746
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8427–8439
Language:
URL:
https://aclanthology.org/2020.acl-main.746
DOI:
10.18653/v1/2020.acl-main.746
Bibkey:
Cite (ACL):
Elias Stengel-Eskin, Aaron Steven White, Sheng Zhang, and Benjamin Van Durme. 2020. Universal Decompositional Semantic Parsing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8427–8439, Online. Association for Computational Linguistics.
Cite (Informal):
Universal Decompositional Semantic Parsing (Stengel-Eskin et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.746.pdf
Video:
 http://slideslive.com/38929022