Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees

Ola Rønning; Daniel Hardt; Anders Søgaard

Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees

Ola Rønning, Daniel Hardt, Anders Søgaard

Department of Digitalization

University of Copenhagen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

111 Downloads (Pure)

Abstract

Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on handcrafted 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.

Original language	English
Title of host publication	Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies
Editors	Stephanie Lukin, Margaret Mitchell
Number of pages	6
Volume	2
Place of Publication	New Orleans, LA
Publisher	Association for Computational Linguistics
Publication date	2018
Pages	236–241
ISBN (Print)	9781948087292
Publication status	Published - 2018
Event	The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - New Orleans, United States Duration: 1 Jun 2018 → 6 Jun 2018 Conference number: 16 http://naacl2018.org/

Conference

Conference	The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics
Number	16
Country/Territory	United States
City	New Orleans
Period	01/06/2018 → 06/06/2018
Internet address	http://naacl2018.org/

Access to Document

N18-2038Final published version, 165 KBLicence: CC BY-NC-ND

http://aclweb.org/anthology/N18-2Licence: Unspecified

Handle.net

Persistent link

Cite this

Rønning, O., Hardt, D., & Søgaard, A. (2018). Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. In S. Lukin, & M. Mitchell (Eds.), Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol. 2, pp. 236–241). Association for Computational Linguistics. http://aclweb.org/anthology/N18-2

Rønning, Ola ; Hardt, Daniel ; Søgaard, Anders. / Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. editor / Stephanie Lukin ; Margaret Mitchell. Vol. 2 New Orleans, LA : Association for Computational Linguistics, 2018. pp. 236–241

@inproceedings{d43ae962a2264b32a45a71caecc5e178,

title = "Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees",

abstract = "Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on handcrafted 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.",

author = "Ola R{\o}nning and Daniel Hardt and Anders S{\o}gaard",

year = "2018",

language = "English",

isbn = "9781948087292",

volume = "2",

pages = "236–241",

editor = "Stephanie Lukin and Margaret Mitchell",

booktitle = "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics ; Conference date: 01-06-2018 Through 06-06-2018",

url = "http://naacl2018.org/",

}

Rønning, O, Hardt, D & Søgaard, A 2018, Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. in S Lukin & M Mitchell (eds), Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. vol. 2, Association for Computational Linguistics, New Orleans, LA, pp. 236–241, The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics, New Orleans, Louisiana, United States, 01/06/2018. <http://aclweb.org/anthology/N18-2>

Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. / Rønning, Ola; Hardt, Daniel; Søgaard, Anders.
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ed. / Stephanie Lukin; Margaret Mitchell. Vol. 2 New Orleans, LA: Association for Computational Linguistics, 2018. p. 236–241.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees

AU - Rønning, Ola

AU - Hardt, Daniel

AU - Søgaard, Anders

N1 - Conference code: 16

PY - 2018

Y1 - 2018

N2 - Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on handcrafted 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.

AB - Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on handcrafted 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.

M3 - Article in proceedings

SN - 9781948087292

VL - 2

SP - 236

EP - 241

BT - Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Lukin, Stephanie

A2 - Mitchell, Margaret

PB - Association for Computational Linguistics

CY - New Orleans, LA

T2 - The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics

Y2 - 1 June 2018 through 6 June 2018

ER -

Rønning O, Hardt D, Søgaard A. Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. In Lukin S, Mitchell M, editors, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Vol. 2. New Orleans, LA: Association for Computational Linguistics. 2018. p. 236–241