Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation

Simon Mille; Anja Belz; Bernd Bohnet; Leo Wanner

doi:10.18653/v1/W18-6527

Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation

Simon Mille, Anja Belz, Bernd Bohnet, Leo Wanner

Applied Data Analytics Research and Enterprise Group

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-review

Abstract

In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR’18).
For the Shallow Track, data in ten languages has been re- leased: Arabic, Czech, Dutch, English, Finnish, French, Italian, Portuguese, Russian and Spanish. For the Deep Track, data in three languages is made available: English, French and Spanish. We describe in detail how the datasets were derived from
the Universal Dependencies V2.0, and report on an evaluation of the Deep Track input quality. In addition, we examine the motivation for, and likely usefulness of, deriving NLG inputs from annotations in resources originally developed for Natural Language Understanding (NLU), and
assess whether the resulting inputs supply enough information of the right kind for the final stage in the NLG process.

Original language	English
Title of host publication	Proceedings of the 11th International Natural Language Generation Conference
Publisher	The Association for Computational Linguistics
DOIs	https://doi.org/10.18653/v1/W18-6527
Publication status	Published - 1 Nov 2018
Event	11th International Conference on Natural Language Generation - Tilburg University, Tilburg, Netherlands Duration: 5 Nov 2018 → 8 Nov 2018 https://inlg2018.uvt.nl/

Conference

Conference	11th International Conference on Natural Language Generation
Abbreviated title	INLG2018
Country/Territory	Netherlands
City	Tilburg
Period	5/11/18 → 8/11/18
Internet address	https://inlg2018.uvt.nl/

Bibliographical note

© The author(s) | ACM 2018. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in {Source Publication}, http://dx.doi.org/10.1145/{number}

Access to Document

10.18653/v1/W18-6527

2018_inlg_SRST_data_CR2Accepted author manuscript, 175 KB

Cite this

@inproceedings{8f0f0eb47351466fb4e9beea383f3136,

title = "Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation",

abstract = "In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR{\textquoteright}18).For the Shallow Track, data in ten languages has been re- leased: Arabic, Czech, Dutch, English, Finnish, French, Italian, Portuguese, Russian and Spanish. For the Deep Track, data in three languages is made available: English, French and Spanish. We describe in detail how the datasets were derived fromthe Universal Dependencies V2.0, and report on an evaluation of the Deep Track input quality. In addition, we examine the motivation for, and likely usefulness of, deriving NLG inputs from annotations in resources originally developed for Natural Language Understanding (NLU), andassess whether the resulting inputs supply enough information of the right kind for the final stage in the NLG process.",

author = "Simon Mille and Anja Belz and Bernd Bohnet and Leo Wanner",

note = "{\textcopyright} The author(s) | ACM 2018. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in {Source Publication}, http://dx.doi.org/10.1145/{number}; 11th International Conference on Natural Language Generation, INLG2018 ; Conference date: 05-11-2018 Through 08-11-2018",

year = "2018",

month = nov,

day = "1",

doi = "10.18653/v1/W18-6527",

language = "English",

booktitle = "Proceedings of the 11th International Natural Language Generation Conference",

publisher = "The Association for Computational Linguistics",

url = "https://inlg2018.uvt.nl/",

}

Mille, S, Belz, A, Bohnet, B & Wanner, L 2018, Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation. in Proceedings of the 11th International Natural Language Generation Conference. The Association for Computational Linguistics, 11th International Conference on Natural Language Generation, Tilburg, Netherlands, 5/11/18. https://doi.org/10.18653/v1/W18-6527

Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation. / Mille, Simon; Belz, Anja; Bohnet, Bernd et al.

Proceedings of the 11th International Natural Language Generation Conference. The Association for Computational Linguistics, 2018.

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-review

TY - GEN

T1 - Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation

AU - Mille, Simon

AU - Belz, Anja

AU - Bohnet, Bernd

AU - Wanner, Leo

N1 - © The author(s) | ACM 2018. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in {Source Publication}, http://dx.doi.org/10.1145/{number}

PY - 2018/11/1

Y1 - 2018/11/1

N2 - In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR’18).For the Shallow Track, data in ten languages has been re- leased: Arabic, Czech, Dutch, English, Finnish, French, Italian, Portuguese, Russian and Spanish. For the Deep Track, data in three languages is made available: English, French and Spanish. We describe in detail how the datasets were derived fromthe Universal Dependencies V2.0, and report on an evaluation of the Deep Track input quality. In addition, we examine the motivation for, and likely usefulness of, deriving NLG inputs from annotations in resources originally developed for Natural Language Understanding (NLU), andassess whether the resulting inputs supply enough information of the right kind for the final stage in the NLG process.

AB - In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR’18).For the Shallow Track, data in ten languages has been re- leased: Arabic, Czech, Dutch, English, Finnish, French, Italian, Portuguese, Russian and Spanish. For the Deep Track, data in three languages is made available: English, French and Spanish. We describe in detail how the datasets were derived fromthe Universal Dependencies V2.0, and report on an evaluation of the Deep Track input quality. In addition, we examine the motivation for, and likely usefulness of, deriving NLG inputs from annotations in resources originally developed for Natural Language Understanding (NLU), andassess whether the resulting inputs supply enough information of the right kind for the final stage in the NLG process.

U2 - 10.18653/v1/W18-6527

DO - 10.18653/v1/W18-6527

M3 - Conference contribution with ISSN or ISBN

BT - Proceedings of the 11th International Natural Language Generation Conference

PB - The Association for Computational Linguistics

T2 - 11th International Conference on Natural Language Generation

Y2 - 5 November 2018 through 8 November 2018

ER -