Summary Explorer: Visualizing the State of the Art in Text Summarization.

Shahbaz Syed; Tariq Yousef; Khalid Al Khatib; Stefan Jänicke; Martin Potthast

doi:10.18653/V1/2021.EMNLP-DEMO.22

Summary Explorer: Visualizing the State of the Art in Text Summarization.

Shahbaz Syed, Tariq Yousef, Khalid Al Khatib, Stefan Jänicke, Martin Potthast

Institut for Matematik og Datalogi

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning

Abstract

This paper introduces Summary Explorer, a new tool to support the manual inspection of text summarization systems by compiling the outputs of 55 state-of-the-art single document summarization approaches on three benchmark datasets, and visually exploring them during a qualitative assessment. The underlying design of the tool considers three well-known summary quality criteria (coverage, faithfulness, and position bias), encapsulated in a guided assessment based on tailored visualizations. The tool complements existing approaches for locally debugging summarization models and improves upon them.

Originalsprog	Engelsk
Titel	Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Forlag	Association for Computational Linguistics
Publikationsdato	2021
Sider	185-194
DOI	https://doi.org/10.18653/V1/2021.EMNLP-DEMO.22
Status	Udgivet - 2021
Begivenhed	The 2021 Conference on Empirical Methods in Natural Language Processing - Punta Cana, Dominikanske Republik, Den Varighed: 7. nov. 2021 → 11. nov. 2021 https://2021.emnlp.org/

Konference

Konference	The 2021 Conference on Empirical Methods in Natural Language Processing
Land/Område	Dominikanske Republik, Den
By	Punta Cana
Periode	07/11/2021 → 11/11/2021
Internetadresse	https://2021.emnlp.org/

Dokumenter og links

10.18653/V1/2021.EMNLP-DEMO.22

Citationsformater

@inproceedings{5e4163d6a31a4e8490bb12727435f175,

title = "Summary Explorer: Visualizing the State of the Art in Text Summarization.",

abstract = "This paper introduces Summary Explorer, a new tool to support the manual inspection of text summarization systems by compiling the outputs of 55 state-of-the-art single document summarization approaches on three benchmark datasets, and visually exploring them during a qualitative assessment. The underlying design of the tool considers three well-known summary quality criteria (coverage, faithfulness, and position bias), encapsulated in a guided assessment based on tailored visualizations. The tool complements existing approaches for locally debugging summarization models and improves upon them. ",

author = "Shahbaz Syed and Tariq Yousef and Khatib, {Khalid Al} and Stefan J{\"a}nicke and Martin Potthast",

year = "2021",

doi = "10.18653/V1/2021.EMNLP-DEMO.22",

language = "English",

pages = "185--194",

booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",

publisher = "Association for Computational Linguistics",

note = "The 2021 Conference on Empirical Methods in Natural Language Processing<br/>, EMNLP 2021 ; Conference date: 07-11-2021 Through 11-11-2021",

url = "https://2021.emnlp.org/",

}

Syed, S, Yousef, T, Khatib, KA, Jänicke, S & Potthast, M 2021, Summary Explorer: Visualizing the State of the Art in Text Summarization. i Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, s. 185-194, The 2021 Conference on Empirical Methods in Natural Language Processing
, Punta Cana, Dominikanske Republik, Den, 07/11/2021. https://doi.org/10.18653/V1/2021.EMNLP-DEMO.22

Summary Explorer: Visualizing the State of the Art in Text Summarization. / Syed, Shahbaz; Yousef, Tariq; Khatib, Khalid Al et al.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, 2021. s. 185-194.

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning

TY - GEN

T1 - Summary Explorer: Visualizing the State of the Art in Text Summarization.

AU - Syed, Shahbaz

AU - Yousef, Tariq

AU - Khatib, Khalid Al

AU - Jänicke, Stefan

AU - Potthast, Martin

PY - 2021

Y1 - 2021

N2 - This paper introduces Summary Explorer, a new tool to support the manual inspection of text summarization systems by compiling the outputs of 55 state-of-the-art single document summarization approaches on three benchmark datasets, and visually exploring them during a qualitative assessment. The underlying design of the tool considers three well-known summary quality criteria (coverage, faithfulness, and position bias), encapsulated in a guided assessment based on tailored visualizations. The tool complements existing approaches for locally debugging summarization models and improves upon them.

AB - This paper introduces Summary Explorer, a new tool to support the manual inspection of text summarization systems by compiling the outputs of 55 state-of-the-art single document summarization approaches on three benchmark datasets, and visually exploring them during a qualitative assessment. The underlying design of the tool considers three well-known summary quality criteria (coverage, faithfulness, and position bias), encapsulated in a guided assessment based on tailored visualizations. The tool complements existing approaches for locally debugging summarization models and improves upon them.

U2 - 10.18653/V1/2021.EMNLP-DEMO.22

DO - 10.18653/V1/2021.EMNLP-DEMO.22

M3 - Article in proceedings

SP - 185

EP - 194

BT - Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

PB - Association for Computational Linguistics

T2 - The 2021 Conference on Empirical Methods in Natural Language Processing<br/>

Y2 - 7 November 2021 through 11 November 2021

ER -

Summary Explorer: Visualizing the State of the Art in Text Summarization.

Abstract

Konference

Dokumenter og links

Fingeraftryk

Citationsformater