The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics

Sebastian Gehrmann; Tosin Adewumi; Karmanya Aggarwal; Pawan Sasanka Ammanamanchi; Aremu Anuoluwapo; Antoine Bosselut; Khyathi Raghavi Chandu; Miruna Clinciu; Dipanjan Das; Kaustubh D. Dhole; Wanyu Du; Esin Durmus; Ondřej Dušek; Chris Emezue; Varun Gangal; Cristina Garbacea; Tatsunori Hashimoto; Yufang Hou; Yacine Jernite; Harsh Jhamtani; Yangfeng Ji; Shailza Jolly; Mihir Kale; Dhruv Kumar; Faisal Ladhak; Aman Madaan; Mounica Maddela; Khyati Mahajan; Saad Mahamood; Bodhisattwa Prasad Majumder; Pedro Henrique Martins; Angelina McMillan-Major; Simon Mille; Emiel van Miltenburg; Moin Nadeem; Shashi Narayan; Vitaly Nikolaev; Rubungo Andre Niyongabo; Salomey Osei; Ankur Parikh; Laura Perez-Beltrachini; Niranjan Ramesh Rao; Vikas Raunak; Juan Diego Rodriguez; Sashank Santhanam; João Sedoc; Thibault Sellam; Samira Shaikh; Anastasia Shimorina; Marco Antonio Sobrevilla Cabezudo; Hendrik Strobelt; Nishant Subramani; Wei Xu; Diyi Yang; Akhila Yerukola; Jiawei Zhou

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics

Sebastian Gehrmann, Tosin Adewumi, Karmanya Aggarwal, Pawan Sasanka Ammanamanchi, Aremu Anuoluwapo, Antoine Bosselut, Khyathi Raghavi Chandu, Miruna Clinciu, Dipanjan Das, Kaustubh D. Dhole, Wanyu Du, Esin Durmus, Ondřej Dušek, Chris Emezue, Varun Gangal, Cristina Garbacea, Tatsunori Hashimoto, Yufang Hou, Yacine Jernite, Harsh JhamtaniYangfeng Ji, Shailza Jolly, Mihir Kale, Dhruv Kumar, Faisal Ladhak, Aman Madaan, Mounica Maddela, Khyati Mahajan, Saad Mahamood, Bodhisattwa Prasad Majumder, Pedro Henrique Martins, Angelina McMillan-Major, Simon Mille, Emiel van Miltenburg, Moin Nadeem, Shashi Narayan, Vitaly Nikolaev, Rubungo Andre Niyongabo, Salomey Osei, Ankur Parikh, Laura Perez-Beltrachini, Niranjan Ramesh Rao, Vikas Raunak, Juan Diego Rodriguez, Sashank Santhanam, João Sedoc, Thibault Sellam, Samira Shaikh, Anastasia Shimorina, Marco Antonio Sobrevilla Cabezudo, Hendrik Strobelt, Nishant Subramani, Wei Xu, Diyi Yang, Akhila Yerukola, Jiawei Zhou

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

166 Citas (Scopus)

Resumen

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.

Idioma original	Inglés
Título de la publicación alojada	GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings
Editores	Antoine Bosselut, Esin Durmus, Varun Prashant Gangal, Sebastian Gehrmann, Yacine Jernite, Laura Perez-Beltrachini, Samira Shaikh, Wei Xu
Editorial	Association for Computational Linguistics (ACL)
Páginas	96-120
Número de páginas	25
ISBN (versión digital)	9781954085671
Estado	Publicada - 2021
Publicado de forma externa	Sí
Evento	1st Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2021 - Virtual, Online, Tailandia Duración: 5 ago. 2021 → 6 ago. 2021

Serie de la publicación

Nombre	GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings

Conferencia

Conferencia	1st Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2021
País/Territorio	Tailandia
Ciudad	Virtual, Online
Período	5/08/21 → 6/08/21

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Gehrmann, S., Adewumi, T., Aggarwal, K., Ammanamanchi, P. S., Anuoluwapo, A., Bosselut, A., Chandu, K. R., Clinciu, M., Das, D., Dhole, K. D., Du, W., Durmus, E., Dušek, O., Emezue, C., Gangal, V., Garbacea, C., Hashimoto, T., Hou, Y., Jernite, Y., ... Zhou, J. (2021). The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics. En A. Bosselut, E. Durmus, V. P. Gangal, S. Gehrmann, Y. Jernite, L. Perez-Beltrachini, S. Shaikh, & W. Xu (Eds.), GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings (pp. 96-120). (GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings). Association for Computational Linguistics (ACL).

Gehrmann, Sebastian ; Adewumi, Tosin ; Aggarwal, Karmanya et al. / The GEM Benchmark : Natural Language Generation, its Evaluation and Metrics. GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings. editor / Antoine Bosselut ; Esin Durmus ; Varun Prashant Gangal ; Sebastian Gehrmann ; Yacine Jernite ; Laura Perez-Beltrachini ; Samira Shaikh ; Wei Xu. Association for Computational Linguistics (ACL), 2021. pp. 96-120 (GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings).

@inproceedings{d59a08d50b0e4d1fbedf603888dd1b6e,

title = "The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics",

abstract = "We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.",

author = "Sebastian Gehrmann and Tosin Adewumi and Karmanya Aggarwal and Ammanamanchi, {Pawan Sasanka} and Aremu Anuoluwapo and Antoine Bosselut and Chandu, {Khyathi Raghavi} and Miruna Clinciu and Dipanjan Das and Dhole, {Kaustubh D.} and Wanyu Du and Esin Durmus and Ond{\v r}ej Du{\v s}ek and Chris Emezue and Varun Gangal and Cristina Garbacea and Tatsunori Hashimoto and Yufang Hou and Yacine Jernite and Harsh Jhamtani and Yangfeng Ji and Shailza Jolly and Mihir Kale and Dhruv Kumar and Faisal Ladhak and Aman Madaan and Mounica Maddela and Khyati Mahajan and Saad Mahamood and Majumder, {Bodhisattwa Prasad} and Martins, {Pedro Henrique} and Angelina McMillan-Major and Simon Mille and {van Miltenburg}, Emiel and Moin Nadeem and Shashi Narayan and Vitaly Nikolaev and Niyongabo, {Rubungo Andre} and Salomey Osei and Ankur Parikh and Laura Perez-Beltrachini and Rao, {Niranjan Ramesh} and Vikas Raunak and Rodriguez, {Juan Diego} and Sashank Santhanam and Jo{\~a}o Sedoc and Thibault Sellam and Samira Shaikh and Anastasia Shimorina and Cabezudo, {Marco Antonio Sobrevilla} and Hendrik Strobelt and Nishant Subramani and Wei Xu and Diyi Yang and Akhila Yerukola and Jiawei Zhou",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics; 1st Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2021 ; Conference date: 05-08-2021 Through 06-08-2021",

year = "2021",

language = "English",

series = "GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings",

publisher = "Association for Computational Linguistics (ACL)",

pages = "96--120",

editor = "Antoine Bosselut and Esin Durmus and Gangal, {Varun Prashant} and Sebastian Gehrmann and Yacine Jernite and Laura Perez-Beltrachini and Samira Shaikh and Wei Xu",

booktitle = "GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings",

}

Gehrmann, S, Adewumi, T, Aggarwal, K, Ammanamanchi, PS, Anuoluwapo, A, Bosselut, A, Chandu, KR, Clinciu, M, Das, D, Dhole, KD, Du, W, Durmus, E, Dušek, O, Emezue, C, Gangal, V, Garbacea, C, Hashimoto, T, Hou, Y, Jernite, Y, Jhamtani, H, Ji, Y, Jolly, S, Kale, M, Kumar, D, Ladhak, F, Madaan, A, Maddela, M, Mahajan, K, Mahamood, S, Majumder, BP, Martins, PH, McMillan-Major, A, Mille, S, van Miltenburg, E, Nadeem, M, Narayan, S, Nikolaev, V, Niyongabo, RA, Osei, S, Parikh, A, Perez-Beltrachini, L, Rao, NR, Raunak, V, Rodriguez, JD, Santhanam, S, Sedoc, J, Sellam, T, Shaikh, S, Shimorina, A, Cabezudo, MAS, Strobelt, H, Subramani, N, Xu, W, Yang, D, Yerukola, A & Zhou, J 2021, The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics. En A Bosselut, E Durmus, VP Gangal, S Gehrmann, Y Jernite, L Perez-Beltrachini, S Shaikh & W Xu (eds.), GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings. GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings, Association for Computational Linguistics (ACL), pp. 96-120, 1st Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2021, Virtual, Online, Tailandia, 5/08/21.

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics. / Gehrmann, Sebastian; Adewumi, Tosin; Aggarwal, Karmanya et al.
GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings. ed. / Antoine Bosselut; Esin Durmus; Varun Prashant Gangal; Sebastian Gehrmann; Yacine Jernite; Laura Perez-Beltrachini; Samira Shaikh; Wei Xu. Association for Computational Linguistics (ACL), 2021. p. 96-120 (GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - The GEM Benchmark

T2 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2021

AU - Gehrmann, Sebastian

AU - Adewumi, Tosin

AU - Aggarwal, Karmanya

AU - Ammanamanchi, Pawan Sasanka

AU - Anuoluwapo, Aremu

AU - Bosselut, Antoine

AU - Chandu, Khyathi Raghavi

AU - Clinciu, Miruna

AU - Das, Dipanjan

AU - Dhole, Kaustubh D.

AU - Du, Wanyu

AU - Durmus, Esin

AU - Dušek, Ondřej

AU - Emezue, Chris

AU - Gangal, Varun

AU - Garbacea, Cristina

AU - Hashimoto, Tatsunori

AU - Hou, Yufang

AU - Jernite, Yacine

AU - Jhamtani, Harsh

AU - Ji, Yangfeng

AU - Jolly, Shailza

AU - Kale, Mihir

AU - Kumar, Dhruv

AU - Ladhak, Faisal

AU - Madaan, Aman

AU - Maddela, Mounica

AU - Mahajan, Khyati

AU - Mahamood, Saad

AU - Majumder, Bodhisattwa Prasad

AU - Martins, Pedro Henrique

AU - McMillan-Major, Angelina

AU - Mille, Simon

AU - van Miltenburg, Emiel

AU - Nadeem, Moin

AU - Narayan, Shashi

AU - Nikolaev, Vitaly

AU - Niyongabo, Rubungo Andre

AU - Osei, Salomey

AU - Parikh, Ankur

AU - Perez-Beltrachini, Laura

AU - Rao, Niranjan Ramesh

AU - Raunak, Vikas

AU - Rodriguez, Juan Diego

AU - Santhanam, Sashank

AU - Sedoc, João

AU - Sellam, Thibault

AU - Shaikh, Samira

AU - Shimorina, Anastasia

AU - Cabezudo, Marco Antonio Sobrevilla

AU - Strobelt, Hendrik

AU - Subramani, Nishant

AU - Xu, Wei

AU - Yang, Diyi

AU - Yerukola, Akhila

AU - Zhou, Jiawei

PY - 2021

Y1 - 2021

N2 - We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.

AB - We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.

UR - http://www.scopus.com/inward/record.url?scp=85121350997&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85121350997

T3 - GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings

SP - 96

EP - 120

BT - GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings

A2 - Bosselut, Antoine

A2 - Durmus, Esin

A2 - Gangal, Varun Prashant

A2 - Gehrmann, Sebastian

A2 - Jernite, Yacine

A2 - Perez-Beltrachini, Laura

A2 - Shaikh, Samira

A2 - Xu, Wei

PB - Association for Computational Linguistics (ACL)

Y2 - 5 August 2021 through 6 August 2021

ER -

Gehrmann S, Adewumi T, Aggarwal K, Ammanamanchi PS, Anuoluwapo A, Bosselut A et al. The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics. En Bosselut A, Durmus E, Gangal VP, Gehrmann S, Jernite Y, Perez-Beltrachini L, Shaikh S, Xu W, editores, GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings. Association for Computational Linguistics (ACL). 2021. p. 96-120. (GEM 2021 - 1st Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings).

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics

Resumen

Serie de la publicación

Conferencia

Otros archivos y enlaces

Huella

Citar esto