How large are lions? Inducing distributions over quantitative attributes

Yanai Elazar; Abhijit Mahabal; Deepak Ramachandran; Tania Bedrax-Weiss; Dan Roth

How large are lions? Inducing distributions over quantitative attributes

Yanai Elazar, Abhijit Mahabal, Deepak Ramachandran, Tania Bedrax-Weiss, Dan Roth

Department of Computer Science

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

37 Scopus citations

Abstract

Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very large resource consisting of distributions over physical quantities associated with objects, adjectives, and verbs which we call Distribution over Quantities (DOQ)¹. This contrasts with recent work in this area which has focused on making only relative comparisons such as “Is a lion bigger than a wolf?”. Our evaluation shows that DOQ compares favorably with state of the art results on existing datasets for relative comparisons of nouns and adjectives, and on a new dataset we introduce.

Original language	English
Title of host publication	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	3973-3983
Number of pages	11
ISBN (Electronic)	9781950737482
State	Published - 2020
Event	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/Territory	Italy
City	Florence
Period	28/07/19 → 2/08/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Funding

We would like to thank Ellie Pavlick, Jason Baldridge, Anne Cocos, Vered Shwartz, Hila Gonen and the 3 anonymous reviewers for helpful comments. Furthermore, we thank Maxwell Forbes, Yiben Yang and Niket Tandon for their helpful clarifications regarding their methods and code. The research of Dan Roth is partly supported by a Google gift and by DARPA, under agreement number HR0011-18-2-0052.

Funders	Funder number
Defense Advanced Research Projects Agency	HR0011-18-2-0052
Google

Cite this

Elazar, Y., Mahabal, A., Ramachandran, D., Bedrax-Weiss, T., & Roth, D. (2020). How large are lions? Inducing distributions over quantitative attributes. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 3973-3983). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Elazar, Yanai ; Mahabal, Abhijit ; Ramachandran, Deepak et al. / How large are lions? Inducing distributions over quantitative attributes. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 3973-3983 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{21b07dc3eaf74571aa115d26ee5a280d,

title = "How large are lions? Inducing distributions over quantitative attributes",

abstract = "Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very large resource consisting of distributions over physical quantities associated with objects, adjectives, and verbs which we call Distribution over Quantities (DOQ)1. This contrasts with recent work in this area which has focused on making only relative comparisons such as “Is a lion bigger than a wolf?”. Our evaluation shows that DOQ compares favorably with state of the art results on existing datasets for relative comparisons of nouns and adjectives, and on a new dataset we introduce.",

author = "Yanai Elazar and Abhijit Mahabal and Deepak Ramachandran and Tania Bedrax-Weiss and Dan Roth",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2020",

language = "אנגלית",

series = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

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

pages = "3973--3983",

booktitle = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "ארצות הברית",

}

Elazar, Y, Mahabal, A, Ramachandran, D, Bedrax-Weiss, T & Roth, D 2020, How large are lions? Inducing distributions over quantitative attributes. in ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 3973-3983, 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 28/07/19.

How large are lions? Inducing distributions over quantitative attributes. / Elazar, Yanai; Mahabal, Abhijit; Ramachandran, Deepak et al.
ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 3973-3983 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

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

TY - GEN

T1 - How large are lions? Inducing distributions over quantitative attributes

AU - Elazar, Yanai

AU - Mahabal, Abhijit

AU - Ramachandran, Deepak

AU - Bedrax-Weiss, Tania

AU - Roth, Dan

PY - 2020

Y1 - 2020

N2 - Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very large resource consisting of distributions over physical quantities associated with objects, adjectives, and verbs which we call Distribution over Quantities (DOQ)1. This contrasts with recent work in this area which has focused on making only relative comparisons such as “Is a lion bigger than a wolf?”. Our evaluation shows that DOQ compares favorably with state of the art results on existing datasets for relative comparisons of nouns and adjectives, and on a new dataset we introduce.

AB - Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very large resource consisting of distributions over physical quantities associated with objects, adjectives, and verbs which we call Distribution over Quantities (DOQ)1. This contrasts with recent work in this area which has focused on making only relative comparisons such as “Is a lion bigger than a wolf?”. Our evaluation shows that DOQ compares favorably with state of the art results on existing datasets for relative comparisons of nouns and adjectives, and on a new dataset we introduce.

UR - https://www.scopus.com/pages/publications/85084052720

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

AN - SCOPUS:85084052720

T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 3973

EP - 3983

BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Elazar Y, Mahabal A, Ramachandran D, Bedrax-Weiss T, Roth D. How large are lions? Inducing distributions over quantitative attributes. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 3973-3983. (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

How large are lions? Inducing distributions over quantitative attributes

Abstract

Publication series

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this