Proposition-Level Clustering for Multi-Document Summarization

Ori Ernst; Avi Caciularu; Ori Shapira; Ramakanth Pasunuru; Mohit Bansal; Jacob Goldberger; Ido Dagan

doi:10.18653/v1/2022.naacl-main.128

Proposition-Level Clustering for Multi-Document Summarization

Ori Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, Ido Dagan

University of North Carolina at Chapel Hill

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

26 Scopus citations

Abstract

Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well as to avoid redundancy. Such prior methods focused on clustering sentences, even though closely related sentences usually contain also non-aligned parts. In this work, we revisit the clustering approach, grouping together sub-sentential propositions, aiming at more precise information alignment. Specifically, our method detects salient propositions, clusters them into paraphrastic clusters, and generates a representative sentence for each cluster via text fusion. Our summarization method improves over the previous state-of-the-art MDS method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.

Original language	English
Title of host publication	NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	1765-1779
Number of pages	15
ISBN (Electronic)	9781955917711
DOIs	https://doi.org/10.18653/v1/2022.naacl-main.128
State	Published - 2022
Event	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - Seattle, United States Duration: 10 Jul 2022 → 15 Jul 2022

Publication series

Name	NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference	2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022
Country/Territory	United States
City	Seattle
Period	10/07/22 → 15/07/22

Bibliographical note

Publisher Copyright:
© 2022 Association for Computational Linguistics.

Funding

The work described herein was supported in part by the PBC fellowship for outstanding PhD candidates in data science, Intel Labs, the Israel Science Foundation grant 2827/21, and by a grant from the Israel Ministry of Science and Technology. Ethical Considerations The work described herein was supported in part by the PBC fellowship for outstanding PhD candidates in data science, Intel Labs, the Israel Science Foundation grant 2827/21, and by a grant from the Israel Ministry of Science and Technology.

Funders	Funder number
Ethical Considerations
Intel Labs
Intel Labs
Israel Science Foundation	2827/21
Ministry of science and technology, Israel
Planning and Budgeting Committee of the Council for Higher Education of Israel

Access to Document

10.18653/v1/2022.naacl-main.128

Cite this

Ernst, O., Caciularu, A., Shapira, O., Pasunuru, R., Bansal, M., Goldberger, J., & Dagan, I. (2022). Proposition-Level Clustering for Multi-Document Summarization. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 1765-1779). (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.naacl-main.128

Ernst, Ori ; Caciularu, Avi ; Shapira, Ori et al. / Proposition-Level Clustering for Multi-Document Summarization. NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2022. pp. 1765-1779 (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

@inproceedings{d3e6ffd9cc414c569e912ab494293aa1,

title = "Proposition-Level Clustering for Multi-Document Summarization",

abstract = "Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well as to avoid redundancy. Such prior methods focused on clustering sentences, even though closely related sentences usually contain also non-aligned parts. In this work, we revisit the clustering approach, grouping together sub-sentential propositions, aiming at more precise information alignment. Specifically, our method detects salient propositions, clusters them into paraphrastic clusters, and generates a representative sentence for each cluster via text fusion. Our summarization method improves over the previous state-of-the-art MDS method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.",

author = "Ori Ernst and Avi Caciularu and Ori Shapira and Ramakanth Pasunuru and Mohit Bansal and Jacob Goldberger and Ido Dagan",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 ; Conference date: 10-07-2022 Through 15-07-2022",

year = "2022",

doi = "10.18653/v1/2022.naacl-main.128",

language = "אנגלית",

series = "NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",

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

pages = "1765--1779",

booktitle = "NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics",

address = "ארצות הברית",

}

Ernst, O, Caciularu, A, Shapira, O, Pasunuru, R, Bansal, M, Goldberger, J & Dagan, I 2022, Proposition-Level Clustering for Multi-Document Summarization. in NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 1765-1779, 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, United States, 10/07/22. https://doi.org/10.18653/v1/2022.naacl-main.128

Proposition-Level Clustering for Multi-Document Summarization. / Ernst, Ori; Caciularu, Avi; Shapira, Ori et al.
NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2022. p. 1765-1779 (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

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

TY - GEN

T1 - Proposition-Level Clustering for Multi-Document Summarization

AU - Ernst, Ori

AU - Caciularu, Avi

AU - Shapira, Ori

AU - Pasunuru, Ramakanth

AU - Bansal, Mohit

AU - Goldberger, Jacob

AU - Dagan, Ido

PY - 2022

Y1 - 2022

N2 - Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well as to avoid redundancy. Such prior methods focused on clustering sentences, even though closely related sentences usually contain also non-aligned parts. In this work, we revisit the clustering approach, grouping together sub-sentential propositions, aiming at more precise information alignment. Specifically, our method detects salient propositions, clusters them into paraphrastic clusters, and generates a representative sentence for each cluster via text fusion. Our summarization method improves over the previous state-of-the-art MDS method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.

AB - Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well as to avoid redundancy. Such prior methods focused on clustering sentences, even though closely related sentences usually contain also non-aligned parts. In this work, we revisit the clustering approach, grouping together sub-sentential propositions, aiming at more precise information alignment. Specifically, our method detects salient propositions, clusters them into paraphrastic clusters, and generates a representative sentence for each cluster via text fusion. Our summarization method improves over the previous state-of-the-art MDS method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.

UR - http://www.scopus.com/inward/record.url?scp=85138412963&partnerID=8YFLogxK

U2 - 10.18653/v1/2022.naacl-main.128

DO - 10.18653/v1/2022.naacl-main.128

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85138412963

T3 - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

SP - 1765

EP - 1779

BT - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022

Y2 - 10 July 2022 through 15 July 2022

ER -

Ernst O, Caciularu A, Shapira O, Pasunuru R, Bansal M, Goldberger J et al. Proposition-Level Clustering for Multi-Document Summarization. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2022. p. 1765-1779. (NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). doi: 10.18653/v1/2022.naacl-main.128

Proposition-Level Clustering for Multi-Document Summarization

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this