Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees

Ola Rønning, Daniel Hardt, Anders Søgaard

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

31 Downloads (Pure)

Abstrakt

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.
OriginalsprogEngelsk
TitelProceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies
RedaktørerStephanie Lukin, Margaret Mitchell
Vol/bind2
Udgivelses stedNew Orleans, LA
ForlagAssociation for Computational Linguistics
Publikationsdato2018
Sider236–241
ISBN (Trykt)9781948087292
StatusUdgivet - 2018
BegivenhedThe 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - New Orleans, USA
Varighed: 1 jun. 20186 jun. 2018
Konferencens nummer: 16
http://naacl2018.org/

Konference

KonferenceThe 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics
Nummer16
LandUSA
ByNew Orleans
Periode01/06/201806/06/2018
Internetadresse

Citationsformater

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