The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023)

Liam Cripwell; Anya Belz; Claire Gardent; Albert Gatt; Claudia Borg; Marthese Borg; John Judge; Michela Lorandi; Anna Nikiforovskaya; William Soto Martinez

The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023)

Liam Cripwell, Anya Belz, Claire Gardent, Albert Gatt, Claudia Borg, Marthese Borg, John Judge, Michela Lorandi, Anna Nikiforovskaya, William Soto Martinez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

The WebNLG task consists of mapping a knowledge graph to a text verbalising the con- tent of that graph. The 2017 WebNLG edi- tion required participating systems to gener- ate English text from a set of DBpedia triples, while the 2020 WebNLG+ challenge addition- ally included generation into Russian and se- mantic parsing of English and Russian texts. In contrast, WebNLG 2023 focuses on four under-resourced languages which are severely under-represented in research on text genera- tion, namely Breton, Irish, Maltese and Welsh. In addition, WebNLG 2023 once again includes Russian. In this paper, we present the organi- sation of the shared task (data, timeline, eval- uation), briefly describe the participating sys- tems and summarise results for participating systems.

Original language	English
Title of host publication	Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023)
Editors	Albert Gatt, Claire Gardent, Liam Cripwell, Anya Belz, Claudia Borg, Aykut Erdem, Erkut Erdem
Publisher	Association for Computational Linguistics
Pages	55-66
Number of pages	12
Publication status	Published - 2023

Keywords

natural language generation
multilinguality
evaluation

Access to Document

2023.mmnlg-1.6Final published version, 503 KBLicence: CC BY

https://aclanthology.org/2023.mmnlg-1.6Licence: CC BY

Cite this

Cripwell, L., Belz, A., Gardent, C., Gatt, A., Borg, C., Borg, M., Judge, J., Lorandi, M., Nikiforovskaya, A., & Soto Martinez, W. (2023). The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023). In A. Gatt, C. Gardent, L. Cripwell, A. Belz, C. Borg, A. Erdem, & E. Erdem (Eds.), Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023) (pp. 55-66). Association for Computational Linguistics. https://aclanthology.org/2023.mmnlg-1.6

Cripwell, Liam ; Belz, Anya ; Gardent, Claire et al. / The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023). Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023). editor / Albert Gatt ; Claire Gardent ; Liam Cripwell ; Anya Belz ; Claudia Borg ; Aykut Erdem ; Erkut Erdem. Association for Computational Linguistics, 2023. pp. 55-66

@inproceedings{2cd476577d00426eb75acc79ae8b9ad1,

title = "The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023)",

abstract = "The WebNLG task consists of mapping a knowledge graph to a text verbalising the con- tent of that graph. The 2017 WebNLG edi- tion required participating systems to gener- ate English text from a set of DBpedia triples, while the 2020 WebNLG+ challenge addition- ally included generation into Russian and se- mantic parsing of English and Russian texts. In contrast, WebNLG 2023 focuses on four under-resourced languages which are severely under-represented in research on text genera- tion, namely Breton, Irish, Maltese and Welsh. In addition, WebNLG 2023 once again includes Russian. In this paper, we present the organi- sation of the shared task (data, timeline, eval- uation), briefly describe the participating sys- tems and summarise results for participating systems.",

keywords = "natural language generation, multilinguality, evaluation",

author = "Liam Cripwell and Anya Belz and Claire Gardent and Albert Gatt and Claudia Borg and Marthese Borg and John Judge and Michela Lorandi and Anna Nikiforovskaya and {Soto Martinez}, William",

year = "2023",

language = "English",

pages = "55--66",

editor = "Gatt, {Albert } and Gardent, {Claire } and Cripwell, {Liam } and Belz, {Anya } and Borg, {Claudia } and Erdem, {Aykut } and Erdem, {Erkut }",

booktitle = "Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023)",

publisher = "Association for Computational Linguistics",

address = "United States",

}

Cripwell, L, Belz, A, Gardent, C, Gatt, A, Borg, C, Borg, M, Judge, J, Lorandi, M, Nikiforovskaya, A & Soto Martinez, W 2023, The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023). in A Gatt, C Gardent, L Cripwell, A Belz, C Borg, A Erdem & E Erdem (eds), Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023). Association for Computational Linguistics, pp. 55-66. <https://aclanthology.org/2023.mmnlg-1.6>

The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023). / Cripwell, Liam; Belz, Anya; Gardent, Claire et al.
Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023). ed. / Albert Gatt; Claire Gardent; Liam Cripwell; Anya Belz; Claudia Borg; Aykut Erdem; Erkut Erdem. Association for Computational Linguistics, 2023. p. 55-66.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023)

AU - Cripwell, Liam

AU - Belz, Anya

AU - Gardent, Claire

AU - Gatt, Albert

AU - Borg, Claudia

AU - Borg, Marthese

AU - Judge, John

AU - Lorandi, Michela

AU - Nikiforovskaya, Anna

AU - Soto Martinez, William

PY - 2023

Y1 - 2023

N2 - The WebNLG task consists of mapping a knowledge graph to a text verbalising the con- tent of that graph. The 2017 WebNLG edi- tion required participating systems to gener- ate English text from a set of DBpedia triples, while the 2020 WebNLG+ challenge addition- ally included generation into Russian and se- mantic parsing of English and Russian texts. In contrast, WebNLG 2023 focuses on four under-resourced languages which are severely under-represented in research on text genera- tion, namely Breton, Irish, Maltese and Welsh. In addition, WebNLG 2023 once again includes Russian. In this paper, we present the organi- sation of the shared task (data, timeline, eval- uation), briefly describe the participating sys- tems and summarise results for participating systems.

AB - The WebNLG task consists of mapping a knowledge graph to a text verbalising the con- tent of that graph. The 2017 WebNLG edi- tion required participating systems to gener- ate English text from a set of DBpedia triples, while the 2020 WebNLG+ challenge addition- ally included generation into Russian and se- mantic parsing of English and Russian texts. In contrast, WebNLG 2023 focuses on four under-resourced languages which are severely under-represented in research on text genera- tion, namely Breton, Irish, Maltese and Welsh. In addition, WebNLG 2023 once again includes Russian. In this paper, we present the organi- sation of the shared task (data, timeline, eval- uation), briefly describe the participating sys- tems and summarise results for participating systems.

KW - natural language generation

KW - multilinguality

KW - evaluation

M3 - Conference contribution

SP - 55

EP - 66

BT - Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023)

A2 - Gatt, Albert

A2 - Gardent, Claire

A2 - Cripwell, Liam

A2 - Belz, Anya

A2 - Borg, Claudia

A2 - Erdem, Aykut

A2 - Erdem, Erkut

PB - Association for Computational Linguistics

ER -

Cripwell L, Belz A, Gardent C, Gatt A, Borg C, Borg M et al. The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023). In Gatt A, Gardent C, Cripwell L, Belz A, Borg C, Erdem A, Erdem E, editors, Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023). Association for Computational Linguistics. 2023. p. 55-66

The 2023 WebNLG Shared Task on Low Resource Languages. Overview and Evaluation Results (WebNLG 2023)

Abstract

Keywords

Access to Document

Fingerprint

Cite this