ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts

Sonia K. Murthy; Kyle Lo; Daniel King; Chandra Bhagavatula; Bailey Kuehl; Sophie Johnson; Jonathan Borchardt; Daniel S. Weld; Tom Hope; Doug Downey

doi:10.18653/v1/2022.emnlp-demos.20

ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts

Sonia K. Murthy
, Kyle Lo
, Daniel King
, Chandra Bhagavatula
, Bailey Kuehl
, Sophie Johnson
, Jonathan Borchardt
, Daniel S. Weld
, Tom Hope
, Doug Downey

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

7 Scopus citations

Abstract

Systems that automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single “best” description per concept, which fails to account for the many ways a concept can be described. We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts. Our system takes advantage of the myriad ways a concept is mentioned across the scientific literature to produce distinct, diverse descriptions of target concepts in terms of different reference concepts. In a user study, we find that users prefer (1) descriptions produced by our end-to-end system, and (2) multiple descriptions to a single “best” description. We release the ACCoRD corpus which includes 1,275 labeled contexts and 1,787 expert-authored concept descriptions to support research on our task.

Original language	English
Title of host publication	EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session
Editors	Wanxiang Che, Ekaterina Shutova
Publisher	Association for Computational Linguistics (ACL)
Pages	200-213
Number of pages	14
ISBN (Electronic)	9781959429418
DOIs	https://doi.org/10.18653/v1/2022.emnlp-demos.20
State	Published - 2022
Externally published	Yes
Event	2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2022 - Abu Dhabi, United Arab Emirates Duration: 7 Dec 2022 → 11 Dec 2022

Publication series

Name	EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session

Conference

Conference	2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2022
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	7/12/22 → 11/12/22

Bibliographical note

Publisher Copyright:
© 2022 Association for Computational Linguistics.

Access to Document

10.18653/v1/2022.emnlp-demos.20

Cite this

Murthy, S. K., Lo, K., King, D., Bhagavatula, C., Kuehl, B., Johnson, S., Borchardt, J., Weld, D. S., Hope, T., & Downey, D. (2022). ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts. In W. Che, & E. Shutova (Eds.), EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session (pp. 200-213). (EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.emnlp-demos.20

Murthy, Sonia K. ; Lo, Kyle ; King, Daniel et al. / ACCoRD : A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts. EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session. editor / Wanxiang Che ; Ekaterina Shutova. Association for Computational Linguistics (ACL), 2022. pp. 200-213 (EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session).

@inproceedings{04bfb81deb4c4bd3976205db7268afb8,

title = "ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts",

abstract = "Systems that automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single “best” description per concept, which fails to account for the many ways a concept can be described. We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts. Our system takes advantage of the myriad ways a concept is mentioned across the scientific literature to produce distinct, diverse descriptions of target concepts in terms of different reference concepts. In a user study, we find that users prefer (1) descriptions produced by our end-to-end system, and (2) multiple descriptions to a single “best” description. We release the ACCoRD corpus which includes 1,275 labeled contexts and 1,787 expert-authored concept descriptions to support research on our task.",

author = "Murthy, \{Sonia K.\} and Kyle Lo and Daniel King and Chandra Bhagavatula and Bailey Kuehl and Sophie Johnson and Jonathan Borchardt and Weld, \{Daniel S.\} and Tom Hope and Doug Downey",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2022 ; Conference date: 07-12-2022 Through 11-12-2022",

year = "2022",

doi = "10.18653/v1/2022.emnlp-demos.20",

language = "אנגלית",

series = "EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session",

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

pages = "200--213",

editor = "Wanxiang Che and Ekaterina Shutova",

booktitle = "EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session",

address = "ארצות הברית",

}

Murthy, SK, Lo, K, King, D, Bhagavatula, C, Kuehl, B, Johnson, S, Borchardt, J, Weld, DS, Hope, T & Downey, D 2022, ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts. in W Che & E Shutova (eds), EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session. EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session, Association for Computational Linguistics (ACL), pp. 200-213, 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2022, Abu Dhabi, United Arab Emirates, 7/12/22. https://doi.org/10.18653/v1/2022.emnlp-demos.20

ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts. / Murthy, Sonia K.; Lo, Kyle; King, Daniel et al.
EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session. ed. / Wanxiang Che; Ekaterina Shutova. Association for Computational Linguistics (ACL), 2022. p. 200-213 (EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session).

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

TY - GEN

T1 - ACCoRD

T2 - 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2022

AU - Murthy, Sonia K.

AU - Lo, Kyle

AU - King, Daniel

AU - Bhagavatula, Chandra

AU - Kuehl, Bailey

AU - Johnson, Sophie

AU - Borchardt, Jonathan

AU - Weld, Daniel S.

AU - Hope, Tom

AU - Downey, Doug

PY - 2022

Y1 - 2022

N2 - Systems that automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single “best” description per concept, which fails to account for the many ways a concept can be described. We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts. Our system takes advantage of the myriad ways a concept is mentioned across the scientific literature to produce distinct, diverse descriptions of target concepts in terms of different reference concepts. In a user study, we find that users prefer (1) descriptions produced by our end-to-end system, and (2) multiple descriptions to a single “best” description. We release the ACCoRD corpus which includes 1,275 labeled contexts and 1,787 expert-authored concept descriptions to support research on our task.

AB - Systems that automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single “best” description per concept, which fails to account for the many ways a concept can be described. We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts. Our system takes advantage of the myriad ways a concept is mentioned across the scientific literature to produce distinct, diverse descriptions of target concepts in terms of different reference concepts. In a user study, we find that users prefer (1) descriptions produced by our end-to-end system, and (2) multiple descriptions to a single “best” description. We release the ACCoRD corpus which includes 1,275 labeled contexts and 1,787 expert-authored concept descriptions to support research on our task.

UR - https://www.scopus.com/pages/publications/85144830679

U2 - 10.18653/v1/2022.emnlp-demos.20

DO - 10.18653/v1/2022.emnlp-demos.20

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

AN - SCOPUS:85144830679

T3 - EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session

SP - 200

EP - 213

BT - EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session

A2 - Che, Wanxiang

A2 - Shutova, Ekaterina

PB - Association for Computational Linguistics (ACL)

Y2 - 7 December 2022 through 11 December 2022

ER -

Murthy SK, Lo K, King D, Bhagavatula C, Kuehl B, Johnson S et al. ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts. In Che W, Shutova E, editors, EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session. Association for Computational Linguistics (ACL). 2022. p. 200-213. (EMNLP 2022 - 2022 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Demonstrations Session). doi: 10.18653/v1/2022.emnlp-demos.20

ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this