Udskriv

Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution

Publikation: KonferencebidragPaperForskningpeer review

Sluicing resolution is the task of identifying the antecedent to a question ellipsis. Antecedents are often sentential constituents, and previous work has therefore relied on syntactic parsing, together with complex linguistic features. A recent model instead used partial parsing as an auxiliary task in sequential neural network architectures to inject syntactic information. We explore the linguistic information being brought to bear by such networks, both by defining subsets of the data exhibiting relevant linguistic characteristics, and by examining the internal representations of the network. Both perspectives provide evidence for substantial linguistic knowledge being deployed by the neural networks.

Publikationsoplysninger

OriginalsprogEngelsk
Publikationsdato2018
Antal sider8
StatusUdgivet - 2018
Begivenhed2018 Conference on Empirical Methods in Natural Language Processing - Square Meeting Center, Brussels, Belgien
Varighed: 31 okt. 20184 nov. 2018
http://emnlp2018.org/

Konference

Konference2018 Conference on Empirical Methods in Natural Language Processing
LokationSquare Meeting Center
LandBelgien
ByBrussels
Periode31/10/201804/11/2018
Internetadresse

ID: 57061355