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 Computer Science

Abstract

Sluice resolution in English is the problemof finding antecedents of wh-fronted ellipses.Previous work has relied on handcraftedfeatures over syntax trees that scalepoorly to other languages and domains;in particular, to dialogue, which is one ofthe most interesting applications of sluiceresolution. Syntactic information is arguablyimportant for sluice resolution, butwe show that multi-task learning with partialparsing as auxiliary tasks effectivelycloses the gap and buys us an additional9% error reduction over previous work.Since we are not directly relying on featuresfrom partial parsers, our system ismore robust to domain shifts, giving a26% error reduction on embedded sluicesin dialogue.

Original language	English
Title of host publication	Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : (Long Papers)
Volume	1
Publisher	Association for Computational Linguistics
Publication date	2018
Pages	236–241
Publication status	Published - 2018
Event	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

Conference	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Country/Territory	United States
City	New Orleans
Period	01/06/2018 → 06/06/2018

Cite this

Sluice resolution without hand-crafted features over brittle syntax trees. / Rønning, Ola; Hardt, Daniel; Søgaard, Anders.
Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : (Long Papers). Vol. 1 Association for Computational Linguistics, 2018. p. 236–241.

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

Rønning, O, Hardt, D & Søgaard, A 2018, Sluice resolution without hand-crafted features over brittle syntax trees. in Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : (Long Papers). vol. 1, Association for Computational Linguistics, pp. 236–241, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, United States, 01/06/2018.

@inproceedings{25dbc9eeb9604fd69bc6299f0b054591,

title = "Sluice resolution without hand-crafted features over brittle syntax trees",

abstract = "Sluice resolution in English is the problemof finding antecedents of wh-fronted ellipses.Previous work has relied on handcraftedfeatures over syntax trees that scalepoorly to other languages and domains;in particular, to dialogue, which is one ofthe most interesting applications of sluiceresolution. Syntactic information is arguablyimportant for sluice resolution, butwe show that multi-task learning with partialparsing as auxiliary tasks effectivelycloses the gap and buys us an additional9% error reduction over previous work.Since we are not directly relying on featuresfrom partial parsers, our system ismore robust to domain shifts, giving a26% error reduction on embedded sluicesin dialogue.",

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

year = "2018",

language = "English",

volume = "1",

pages = "236–241",

booktitle = "Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",

publisher = "Association for Computational Linguistics",

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

}

TY - GEN

T1 - Sluice resolution without hand-crafted features over brittle syntax trees

AU - Rønning, Ola

AU - Hardt, Daniel

AU - Søgaard, Anders

PY - 2018

Y1 - 2018

N2 - Sluice resolution in English is the problemof finding antecedents of wh-fronted ellipses.Previous work has relied on handcraftedfeatures over syntax trees that scalepoorly to other languages and domains;in particular, to dialogue, which is one ofthe most interesting applications of sluiceresolution. Syntactic information is arguablyimportant for sluice resolution, butwe show that multi-task learning with partialparsing as auxiliary tasks effectivelycloses the gap and buys us an additional9% error reduction over previous work.Since we are not directly relying on featuresfrom partial parsers, our system ismore robust to domain shifts, giving a26% error reduction on embedded sluicesin dialogue.

AB - Sluice resolution in English is the problemof finding antecedents of wh-fronted ellipses.Previous work has relied on handcraftedfeatures over syntax trees that scalepoorly to other languages and domains;in particular, to dialogue, which is one ofthe most interesting applications of sluiceresolution. Syntactic information is arguablyimportant for sluice resolution, butwe show that multi-task learning with partialparsing as auxiliary tasks effectivelycloses the gap and buys us an additional9% error reduction over previous work.Since we are not directly relying on featuresfrom partial parsers, our system ismore robust to domain shifts, giving a26% error reduction on embedded sluicesin dialogue.

M3 - Article in proceedings

VL - 1

SP - 236

EP - 241

BT - Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics

T2 - 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Y2 - 1 June 2018 through 6 June 2018

ER -