Syntactic Scaffolds for Semantic Structures

Swabha Swayamdipta, Sam Thomson, Kenton Lee, Luke Zettlemoyer, Chris Dyer, Noah A. Smith


Abstract
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a treebank during training, through a multitask objective. We improve over strong baselines on PropBank semantics, frame semantics, and coreference resolution, achieving competitive performance on all three tasks.
Anthology ID:
D18-1412
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3772–3782
Language:
URL:
https://aclanthology.org/D18-1412
DOI:
10.18653/v1/D18-1412
Bibkey:
Cite (ACL):
Swabha Swayamdipta, Sam Thomson, Kenton Lee, Luke Zettlemoyer, Chris Dyer, and Noah A. Smith. 2018. Syntactic Scaffolds for Semantic Structures. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3772–3782, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Syntactic Scaffolds for Semantic Structures (Swayamdipta et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1412.pdf
Attachment:
 D18-1412.Attachment.zip
Video:
 https://vimeo.com/306118515
Code
 swabhs/scaffolding
Data
FrameNetOntoNotes 5.0