Joint Universal Syntactic and Semantic Parsing

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


Abstract
While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other. This trade-off contradicts the large body of research focusing on the rich interactions at the syntax–semantics interface. We explore multiple model architectures that allow us to exploit the rich syntactic and semantic annotations contained in the Universal Decompositional Semantics (UDS) dataset, jointly parsing Universal Dependencies and UDS to obtain state-of-the-art results in both formalisms. We analyze the behavior of a joint model of syntax and semantics, finding patterns supported by linguistic theory at the syntax–semantics interface. We then investigate to what degree joint modeling generalizes to a multilingual setting, where we find similar trends across 8 languages.
Anthology ID:
2021.tacl-1.46
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
756–773
Language:
URL:
https://aclanthology.org/2021.tacl-1.46
DOI:
10.1162/tacl_a_00396
Bibkey:
Cite (ACL):
Elias Stengel-Eskin, Kenton Murray, Sheng Zhang, Aaron Steven White, and Benjamin Van Durme. 2021. Joint Universal Syntactic and Semantic Parsing. Transactions of the Association for Computational Linguistics, 9:756–773.
Cite (Informal):
Joint Universal Syntactic and Semantic Parsing (Stengel-Eskin et al., TACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.tacl-1.46.pdf
Video:
 https://preview.aclanthology.org/emnlp-22-attachments/2021.tacl-1.46.mp4