A Two-Sided Discussion of Preregistration of NLP Research

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Dokumenter

  • Fullrext

    Forlagets udgivne version, 214 KB, PDF-dokument

Van Miltenburg et al. (2021) suggest NLP research should adopt preregistration to prevent fishing expeditions and to promote publication of negative results. At face value, this is a very reasonable suggestion, seemingly solving many methodological problems with NLP research. We discuss pros and cons-some old, some new: a) Preregistration is challenged by the practice of retrieving hypotheses after the results are known; b) preregistration may bias NLP toward confirmatory research; c) preregistration must allow for reclassification of research as exploratory; d) preregistration may increase publication bias; e) preregistration may increase flag-planting; f) preregistration may increase p-hacking; and finally, g) preregistration may make us less risk tolerant. We cast our discussion as a dialogue, presenting both sides of the debate.

OriginalsprogEngelsk
TitelEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
ForlagAssociation for Computational Linguistics (ACL)
Publikationsdato2023
Sider83-93
ISBN (Elektronisk)9781959429449
DOI
StatusUdgivet - 2023
Begivenhed17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Dubrovnik, Kroatien
Varighed: 2 maj 20236 maj 2023

Konference

Konference17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023
LandKroatien
ByDubrovnik
Periode02/05/202306/05/2023
SponsorAdobe, Babelscape, Bloomberg Engineering, Duolingo, Liveperson

Bibliografisk note

Funding Information:
Thanks to Asbjørn Hróbjartsson and Klemens Kappel for providing us with a helpful overview of the literature on preregistration in epidemiology. Thanks to our anonymous reviewers, as well as all of CoAStaL, for useful feedback on the above discussion. Anders Søgaard received financial support from Innovation Fund Denmark, Google Focused Research Awards, and the Novo Nordisk Foundation.

Funding Information:
Thanks to Asbjørn Hróbjartsson and Klemens Kap-pel for providing us with a helpful overview of the literature on preregistration in epidemiology. Thanks to our anonymous reviewers, as well as all of CoAStaL, for useful feedback on the above discussion. Anders Søgaard received financial support from Innovation Fund Denmark, Google Focused

Publisher Copyright:
© 2023 Association for Computational Linguistics.

ID: 356885601