Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees

Ola Rønning, Daniel Hardt, Anders Søgaard


Abstract
Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on hand-crafted features over syntax trees that scale poorly to other languages and domains; in particular, to dialogue, which is one of the most interesting applications of sluice resolution. Syntactic information is arguably important for sluice resolution, but we show that multi-task learning with partial parsing as auxiliary tasks effectively closes the gap and buys us an additional 9% error reduction over previous work. Since we are not directly relying on features from partial parsers, our system is more robust to domain shifts, giving a 26% error reduction on embedded sluices in dialogue.
Anthology ID:
N18-2038
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
236–241
Language:
URL:
https://aclanthology.org/N18-2038
DOI:
10.18653/v1/N18-2038
Bibkey:
Cite (ACL):
Ola Rønning, Daniel Hardt, and Anders Søgaard. 2018. Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 236–241, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees (Rønning et al., NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/N18-2038.pdf
Dataset:
 N18-2038.Datasets.zip