Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution

Ola Rønning; Daniel Hardt; Anders Søgaard

Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution

Ola Rønning, Daniel Hardt, Anders Søgaard

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

105 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	Proceedings of the 2018 EMNLP Workshop BlackboxNLP : Analyzing and Interpreting Neural Networks for NLP
Editors	Tal Linzen, Grzegorz Chrupała, Afra Alishahi
Number of pages	8
Place of Publication	Brussels
Publisher	Association for Computational Linguistics
Publication date	2018
Pages	66-73
ISBN (Electronic)	9781948087711
Publication status	Published - 2018
Event	2018 Conference on Empirical Methods in Natural Language Processing - Square Meeting Center, Brussels, Belgium Duration: 31 Oct 2018 → 4 Nov 2018 http://emnlp2018.org/

Conference

Conference	2018 Conference on Empirical Methods in Natural Language Processing
Location	Square Meeting Center
Country/Territory	Belgium
City	Brussels
Period	31/10/2018 → 04/11/2018
Internet address	http://emnlp2018.org/

Access to Document

Rønning_Hardt_SøgaardFinal published version, 361 KBLicence: CC BY-NC-ND

Handle.net

Persistent link

Cite this

@inproceedings{c02eca9a86d54a72abaf7b228d81ea62,

title = "Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution",

abstract = "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.",

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

year = "2018",

language = "English",

pages = "66--73",

editor = "Tal Linzen and Grzegorz Chrupa{\l}a and Afra Alishahi",

booktitle = "Proceedings of the 2018 EMNLP Workshop BlackboxNLP",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "2018 Conference on Empirical Methods in Natural Language Processing ; Conference date: 31-10-2018 Through 04-11-2018",

url = "http://emnlp2018.org/",

}

Rønning, O, Hardt, D & Søgaard, A 2018, Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution. in T Linzen, G Chrupała & A Alishahi (eds), Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, Brussels, pp. 66-73, 2018 Conference on Empirical Methods in Natural Language Processing , Brussels, Belgium, 31/10/2018.

Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution. / Rønning, Ola; Hardt, Daniel; Søgaard, Anders.
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. ed. / Tal Linzen; Grzegorz Chrupała; Afra Alishahi. Brussels: Association for Computational Linguistics, 2018. p. 66-73.

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

TY - GEN

T1 - Linguistic Representations in Multi-task Neural Networks for Ellipsis Resolution

AU - Rønning, Ola

AU - Hardt, Daniel

AU - Søgaard, Anders

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

M3 - Article in proceedings

SP - 66

EP - 73

BT - Proceedings of the 2018 EMNLP Workshop BlackboxNLP

A2 - Linzen, Tal

A2 - Chrupała, Grzegorz

A2 - Alishahi, Afra

PB - Association for Computational Linguistics

CY - Brussels

T2 - 2018 Conference on Empirical Methods in Natural Language Processing

Y2 - 31 October 2018 through 4 November 2018

ER -