Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies

Shuhei Kurita; Anders Søgaard

doi:10.18653/v1/P19-1232

Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies

Shuhei Kurita, Anders Søgaard

Machine Learning

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

121 Downloads (Pure)

Abstract

In Semantic Dependency Parsing (SDP), semantic relations form directed acyclic graphs, rather than trees. We propose a new iterative predicate selection (IPS) algorithm for SDP. Our IPS algorithm combines the graph-based and transition-based parsing approaches in order to handle multiple semantic head words. We train the IPS model using a combination of multi-task learning and task-specific policy gradient training. Trained this way, IPS achieves a new state of the art on the SemEval 2015 Task 18 datasets. Furthermore, we observe that policy gradient training learns an easy-first strategy.

Originalsprog	Engelsk
Titel	Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Forlag	Association for Computational Linguistics
Publikationsdato	2019
Sider	2420-2430
DOI	https://doi.org/10.18653/v1/P19-1232
Status	Udgivet - 2019
Begivenhed	57th Annual Meeting of the Association for Computational Linguistics - Florence, Italien Varighed: 1 jul. 2019 → 1 jul. 2019

Konference

Konference	57th Annual Meeting of the Association for Computational Linguistics
Land/Område	Italien
By	Florence,
Periode	01/07/2019 → 01/07/2019

Adgang til dokumentet

10.18653/v1/P19-1232

OA-Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First StrategiesForlagets udgivne version, 3,4 MBLicens: CC BY

Biblioteksadgang?

Tjek tilgængelighed hos det Kgl. Bibliotek

Citationsformater

Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies. / Kurita, Shuhei; Søgaard, Anders.
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2019. s. 2420-2430.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Kurita, S & Søgaard, A 2019, Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies. i Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, s. 2420-2430, 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italien, 01/07/2019. https://doi.org/10.18653/v1/P19-1232

@inproceedings{4fdb0f500f3f4ad1a82a97b9d154ad20,

title = "Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies",

abstract = "In Semantic Dependency Parsing (SDP), semantic relations form directed acyclic graphs, rather than trees. We propose a new iterative predicate selection (IPS) algorithm for SDP. Our IPS algorithm combines the graph-based and transition-based parsing approaches in order to handle multiple semantic head words. We train the IPS model using a combination of multi-task learning and task-specific policy gradient training. Trained this way, IPS achieves a new state of the art on the SemEval 2015 Task 18 datasets. Furthermore, we observe that policy gradient training learns an easy-first strategy.",

author = "Shuhei Kurita and Anders S{\o}gaard",

year = "2019",

doi = "10.18653/v1/P19-1232",

language = "English",

pages = "2420--2430",

booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "57th Annual Meeting of the Association for Computational Linguistics ; Conference date: 01-07-2019 Through 01-07-2019",

}

TY - GEN

T1 - Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies

AU - Kurita, Shuhei

AU - Søgaard, Anders

PY - 2019

Y1 - 2019

N2 - In Semantic Dependency Parsing (SDP), semantic relations form directed acyclic graphs, rather than trees. We propose a new iterative predicate selection (IPS) algorithm for SDP. Our IPS algorithm combines the graph-based and transition-based parsing approaches in order to handle multiple semantic head words. We train the IPS model using a combination of multi-task learning and task-specific policy gradient training. Trained this way, IPS achieves a new state of the art on the SemEval 2015 Task 18 datasets. Furthermore, we observe that policy gradient training learns an easy-first strategy.

AB - In Semantic Dependency Parsing (SDP), semantic relations form directed acyclic graphs, rather than trees. We propose a new iterative predicate selection (IPS) algorithm for SDP. Our IPS algorithm combines the graph-based and transition-based parsing approaches in order to handle multiple semantic head words. We train the IPS model using a combination of multi-task learning and task-specific policy gradient training. Trained this way, IPS achieves a new state of the art on the SemEval 2015 Task 18 datasets. Furthermore, we observe that policy gradient training learns an easy-first strategy.

U2 - 10.18653/v1/P19-1232

DO - 10.18653/v1/P19-1232

M3 - Article in proceedings

SP - 2420

EP - 2430

BT - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 57th Annual Meeting of the Association for Computational Linguistics

Y2 - 1 July 2019 through 1 July 2019

ER -