The WebNLG Challenge: Generating Text from RDF Data

Claire  Gardent; Anastasia Shimorina; Shashi Narayan; Laura  Perez-Beltrachini

doi:10.18653/v1/W17-3518

The WebNLG Challenge: Generating Text from RDF Data

Claire Gardent, Anastasia Shimorina, Shashi Narayan, Laura Perez-Beltrachini

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The WebNLG challenge consists in mapping sets of RDF triples to text. It provides a common benchmark on which to train, evaluate and compare “microplanners”, i.e. generation systems that verbalise a given content by making a range of complex interacting choices including referring expression generation, aggregation, lexicalisation, surface realisation and sentence segmentation. In this paper, we introduce the microplanning task, describe data preparation, introduce our evaluation methodology, analyse participant results and provide a brief description of the participating systems.

Original language	English
Title of host publication	Proceedings of the 10th International Natural Language Generation conference (INLG)
Publisher	ACL Anthology
Pages	124–133
Number of pages	10
DOIs	https://doi.org/10.18653/v1/W17-3518
Publication status	Published - 7 Sep 2017
Event	10th International Conference on Natural Language Generation - Santiago de Compostela, Spain Duration: 4 Sep 2017 → 7 Sep 2017 https://eventos.citius.usc.es/inlg2017/index

Conference

Conference	10th International Conference on Natural Language Generation
Abbreviated title	INLG 2017
Country/Territory	Spain
City	Santiago de Compostela
Period	4/09/17 → 7/09/17
Internet address	https://eventos.citius.usc.es/inlg2017/index

Access to Document

10.18653/v1/W17-3518Licence: Creative Commons: Attribution (CC-BY)

webnlg-challenge-reportAccepted author manuscript, 194 KB

https://aclweb.org/anthology/papers/W/W17/W17-3518/Licence: Creative Commons: Attribution (CC-BY)

SUMMA - Scalable Understanding of Mulitingual Media
Renals, S., Birch-Mayne, A. & Cohen, S.
EU government bodies
1/02/16 → 31/01/19
Project: Research

Cite this

@inproceedings{bd6c5c77b1fc4e95810b272ff4e6cec2,

title = "The WebNLG Challenge: Generating Text from RDF Data",

abstract = "The WebNLG challenge consists in mapping sets of RDF triples to text. It provides a common benchmark on which to train, evaluate and compare “microplanners”, i.e. generation systems that verbalise a given content by making a range of complex interacting choices including referring expression generation, aggregation, lexicalisation, surface realisation and sentence segmentation. In this paper, we introduce the microplanning task, describe data preparation, introduce our evaluation methodology, analyse participant results and provide a brief description of the participating systems.",

author = "Claire Gardent and Anastasia Shimorina and Shashi Narayan and Laura Perez-Beltrachini",

year = "2017",

month = sep,

day = "7",

doi = "10.18653/v1/W17-3518",

language = "English",

pages = "124–133",

booktitle = "Proceedings of the 10th International Natural Language Generation conference (INLG)",

publisher = "ACL Anthology",

note = "10th International Conference on Natural Language Generation, INLG 2017 ; Conference date: 04-09-2017 Through 07-09-2017",

url = "https://eventos.citius.usc.es/inlg2017/index",

}

Gardent, C, Shimorina, A, Narayan, S & Perez-Beltrachini, L 2017, The WebNLG Challenge: Generating Text from RDF Data. in Proceedings of the 10th International Natural Language Generation conference (INLG). ACL Anthology, pp. 124–133, 10th International Conference on Natural Language Generation, Santiago de Compostela, Spain, 4/09/17. https://doi.org/10.18653/v1/W17-3518

TY - GEN

T1 - The WebNLG Challenge: Generating Text from RDF Data

AU - Gardent, Claire

AU - Shimorina, Anastasia

AU - Narayan, Shashi

AU - Perez-Beltrachini, Laura

PY - 2017/9/7

Y1 - 2017/9/7

N2 - The WebNLG challenge consists in mapping sets of RDF triples to text. It provides a common benchmark on which to train, evaluate and compare “microplanners”, i.e. generation systems that verbalise a given content by making a range of complex interacting choices including referring expression generation, aggregation, lexicalisation, surface realisation and sentence segmentation. In this paper, we introduce the microplanning task, describe data preparation, introduce our evaluation methodology, analyse participant results and provide a brief description of the participating systems.

AB - The WebNLG challenge consists in mapping sets of RDF triples to text. It provides a common benchmark on which to train, evaluate and compare “microplanners”, i.e. generation systems that verbalise a given content by making a range of complex interacting choices including referring expression generation, aggregation, lexicalisation, surface realisation and sentence segmentation. In this paper, we introduce the microplanning task, describe data preparation, introduce our evaluation methodology, analyse participant results and provide a brief description of the participating systems.

U2 - 10.18653/v1/W17-3518

DO - 10.18653/v1/W17-3518

M3 - Conference contribution

SP - 124

EP - 133

BT - Proceedings of the 10th International Natural Language Generation conference (INLG)

PB - ACL Anthology

T2 - 10th International Conference on Natural Language Generation

Y2 - 4 September 2017 through 7 September 2017

ER -

The WebNLG Challenge: Generating Text from RDF Data

Abstract

Conference

Access to Document

Fingerprint

Projects

SUMMA - Scalable Understanding of Mulitingual Media

Cite this