Erratum to: Measuring and improving consistency in pretrained language models (Transactions of the Association for Computational Linguistics)

Yanai Elazar; Nora Kassner; Shauli Ravfogel; Abhilasha Ravichander; Eduard Hovy; Hinrich Schütze; Yoav Goldberg

doi:https://doi.org/10.1162/tacl_x_00455

Erratum to: Measuring and improving consistency in pretrained language models (Transactions of the Association for Computational Linguistics)

Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg

Research output: Contribution to journal › Comment/debate

Abstract

During production of this paper, an error was introduced to the formula on the bottom of the right column of page 1020. In the last two terms of the formula, the n and m subscripts were swapped. The correct formula is: k∑ L_c = n=1m=n+1 k∑ D_KL (Q^ri n ‖Q^ri m)+D_KL (Q^ri m‖Q^ri n ) The paper has been updated.

Original language	American English
Pages (from-to)	1407
Number of pages	1
Journal	Transactions of the Association for Computational Linguistics
Volume	9
DOIs	https://doi.org/10.1162/tacl_x_00455
State	Published - 6 Dec 2021
Externally published	Yes

All Science Journal Classification (ASJC) codes

Communication
Human-Computer Interaction
Linguistics and Language
Computer Science Applications
Artificial Intelligence

Access to Document

https://doi.org/10.1162/tacl_x_00455

Cite this

@article{900623a47e7947eeb4e3bd163e9c5c5e,

title = "Erratum to: Measuring and improving consistency in pretrained language models (Transactions of the Association for Computational Linguistics)",

abstract = "During production of this paper, an error was introduced to the formula on the bottom of the right column of page 1020. In the last two terms of the formula, the n and m subscripts were swapped. The correct formula is: k∑ Lc = n=1m=n+1 k∑ DKL (Qri n ‖Qri m)+DKL (Qri m‖Qri n ) The paper has been updated.",

author = "Yanai Elazar and Nora Kassner and Shauli Ravfogel and Abhilasha Ravichander and Eduard Hovy and Hinrich Sch{\"u}tze and Yoav Goldberg",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license.",

year = "2021",

month = dec,

day = "6",

doi = "https://doi.org/10.1162/tacl_x_00455",

language = "American English",

volume = "9",

pages = "1407",

journal = "Transactions of the Association for Computational Linguistics",

issn = "2307-387X",

publisher = "MIT Press Journals",

}

TY - JOUR

T1 - Erratum to

T2 - Measuring and improving consistency in pretrained language models (Transactions of the Association for Computational Linguistics)

AU - Elazar, Yanai

AU - Kassner, Nora

AU - Ravfogel, Shauli

AU - Ravichander, Abhilasha

AU - Hovy, Eduard

AU - Schütze, Hinrich

AU - Goldberg, Yoav

PY - 2021/12/6

Y1 - 2021/12/6

N2 - During production of this paper, an error was introduced to the formula on the bottom of the right column of page 1020. In the last two terms of the formula, the n and m subscripts were swapped. The correct formula is: k∑ Lc = n=1m=n+1 k∑ DKL (Qri n ‖Qri m)+DKL (Qri m‖Qri n ) The paper has been updated.

AB - During production of this paper, an error was introduced to the formula on the bottom of the right column of page 1020. In the last two terms of the formula, the n and m subscripts were swapped. The correct formula is: k∑ Lc = n=1m=n+1 k∑ DKL (Qri n ‖Qri m)+DKL (Qri m‖Qri n ) The paper has been updated.

UR - http://www.scopus.com/inward/record.url?scp=85120973482&partnerID=8YFLogxK

U2 - https://doi.org/10.1162/tacl_x_00455

DO - https://doi.org/10.1162/tacl_x_00455

M3 - Comment/debate

SN - 2307-387X

VL - 9

SP - 1407

JO - Transactions of the Association for Computational Linguistics

JF - Transactions of the Association for Computational Linguistics

ER -

Erratum to: Measuring and improving consistency in pretrained language models (Transactions of the Association for Computational Linguistics)

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this