SUMMHELPER: Collaborative Human-Computer Summarization

Aviv Slobodkin; Niv Nachum; Shmuel Amar; Ori Shapira; Ido Dagan

doi:10.18653/v1/2023.emnlp-demo.50

SUMMHELPER: Collaborative Human-Computer Summarization

Aviv Slobodkin, Niv Nachum, Shmuel Amar, Ori Shapira, Ido Dagan

Amazon.com, Inc.

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SUMMHELPER,¹ a 2-phase summarization assistant designed to foster human-machine collaboration. The initial phase involves content selection, where the system recommends potential content, allowing users to accept, modify, or introduce additional selections. The subsequent phase, content consolidation, involves SUMMHELPER generating a coherent summary from these selections, which users can then refine using visual mappings between the summary and the source text. Small-scale user studies reveal the effectiveness of our application, with participants being especially appreciative of the balance between automated guidance and opportunities for personal input.

Original language	English
Pages	554-565
Number of pages	12
DOIs	https://doi.org/10.18653/v1/2023.emnlp-demo.50
State	Published - 2023
Event	2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2023 - Singapore, Singapore Duration: 6 Dec 2023 → 10 Dec 2023

Conference

Conference	2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2023
Country/Territory	Singapore
City	Singapore
Period	6/12/23 → 10/12/23

Bibliographical note

Publisher Copyright:
© 2023 Association for Computational Linguistics.

Funding

This work was supported by the Israel Science Foundation (grant no. 2827/21), and a grant from the Israel Ministry of Science and Technology. We would also like to thank Hadar Ronen for her guidance in planning the user studies.

Funders	Funder number
Israel Science Foundation	2827/21
Ministry of science and technology, Israel

Access to Document

10.18653/v1/2023.emnlp-demo.50

https://aclanthology.org/2023.emnlp-demo.50.pdfLicense: CC BY

Cite this

@conference{90e714762a154b38a4658137b0b2ffa3,

title = "SUMMHELPER: Collaborative Human-Computer Summarization",

abstract = "Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SUMMHELPER,1 a 2-phase summarization assistant designed to foster human-machine collaboration. The initial phase involves content selection, where the system recommends potential content, allowing users to accept, modify, or introduce additional selections. The subsequent phase, content consolidation, involves SUMMHELPER generating a coherent summary from these selections, which users can then refine using visual mappings between the summary and the source text. Small-scale user studies reveal the effectiveness of our application, with participants being especially appreciative of the balance between automated guidance and opportunities for personal input.",

author = "Aviv Slobodkin and Niv Nachum and Shmuel Amar and Ori Shapira and Ido Dagan",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2023 ; Conference date: 06-12-2023 Through 10-12-2023",

year = "2023",

doi = "10.18653/v1/2023.emnlp-demo.50",

language = "אנגלית",

pages = "554--565",

}

TY - CONF

T1 - SUMMHELPER

T2 - 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2023

AU - Slobodkin, Aviv

AU - Nachum, Niv

AU - Amar, Shmuel

AU - Shapira, Ori

AU - Dagan, Ido

PY - 2023

Y1 - 2023

N2 - Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SUMMHELPER,1 a 2-phase summarization assistant designed to foster human-machine collaboration. The initial phase involves content selection, where the system recommends potential content, allowing users to accept, modify, or introduce additional selections. The subsequent phase, content consolidation, involves SUMMHELPER generating a coherent summary from these selections, which users can then refine using visual mappings between the summary and the source text. Small-scale user studies reveal the effectiveness of our application, with participants being especially appreciative of the balance between automated guidance and opportunities for personal input.

AB - Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SUMMHELPER,1 a 2-phase summarization assistant designed to foster human-machine collaboration. The initial phase involves content selection, where the system recommends potential content, allowing users to accept, modify, or introduce additional selections. The subsequent phase, content consolidation, involves SUMMHELPER generating a coherent summary from these selections, which users can then refine using visual mappings between the summary and the source text. Small-scale user studies reveal the effectiveness of our application, with participants being especially appreciative of the balance between automated guidance and opportunities for personal input.

UR - http://www.scopus.com/inward/record.url?scp=85184661947&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.emnlp-demo.50

DO - 10.18653/v1/2023.emnlp-demo.50

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:85184661947

SP - 554

EP - 565

Y2 - 6 December 2023 through 10 December 2023

ER -

SUMMHELPER: Collaborative Human-Computer Summarization

Abstract

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this