@inproceedings{fries-etal-2022-dataset,
title = "Dataset Debt in Biomedical Language Modeling",
author = "Fries, Jason and
Seelam, Natasha and
Altay, Gabriel and
Weber, Leon and
Kang, Myungsun and
Datta, Debajyoti and
Su, Ruisi and
Garda, Samuele and
Wang, Bo and
Ott, Simon and
Samwald, Matthias and
Kusa, Wojciech",
editor = "Fan, Angela and
Ilic, Suzana and
Wolf, Thomas and
Gall{\'e}, Matthias",
booktitle = "Proceedings of BigScience Episode {\#}5 -- Workshop on Challenges {\&} Perspectives in Creating Large Language Models",
month = may,
year = "2022",
address = "virtual+Dublin",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bigscience-1.10",
doi = "10.18653/v1/2022.bigscience-1.10",
pages = "137--145",
abstract = "Large-scale language modeling and natural language prompting have demonstrated exciting capabilities for few and zero shot learning in NLP. However, translating these successes to specialized domains such as biomedicine remains challenging, due in part to biomedical NLP{'}s significant dataset debt {--} the technical costs associated with data that are not consistently documented or easily incorporated into popular machine learning frameworks at scale. To assess this debt, we crowdsourced curation of datasheets for 167 biomedical datasets. We find that only 13{\%} of datasets are available via programmatic access and 30{\%} lack any documentation on licensing and permitted reuse. Our dataset catalog is available at: \url{https://tinyurl.com/bigbio22}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fries-etal-2022-dataset">
<titleInfo>
<title>Dataset Debt in Biomedical Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Fries</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natasha</namePart>
<namePart type="family">Seelam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Altay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Weber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myungsun</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debajyoti</namePart>
<namePart type="family">Datta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruisi</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuele</namePart>
<namePart type="family">Garda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Samwald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wojciech</namePart>
<namePart type="family">Kusa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of BigScience Episode #5 – Workshop on Challenges & Perspectives in Creating Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzana</namePart>
<namePart type="family">Ilic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Gallé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">virtual+Dublin</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale language modeling and natural language prompting have demonstrated exciting capabilities for few and zero shot learning in NLP. However, translating these successes to specialized domains such as biomedicine remains challenging, due in part to biomedical NLP’s significant dataset debt – the technical costs associated with data that are not consistently documented or easily incorporated into popular machine learning frameworks at scale. To assess this debt, we crowdsourced curation of datasheets for 167 biomedical datasets. We find that only 13% of datasets are available via programmatic access and 30% lack any documentation on licensing and permitted reuse. Our dataset catalog is available at: https://tinyurl.com/bigbio22.</abstract>
<identifier type="citekey">fries-etal-2022-dataset</identifier>
<identifier type="doi">10.18653/v1/2022.bigscience-1.10</identifier>
<location>
<url>https://aclanthology.org/2022.bigscience-1.10</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>137</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dataset Debt in Biomedical Language Modeling
%A Fries, Jason
%A Seelam, Natasha
%A Altay, Gabriel
%A Weber, Leon
%A Kang, Myungsun
%A Datta, Debajyoti
%A Su, Ruisi
%A Garda, Samuele
%A Wang, Bo
%A Ott, Simon
%A Samwald, Matthias
%A Kusa, Wojciech
%Y Fan, Angela
%Y Ilic, Suzana
%Y Wolf, Thomas
%Y Gallé, Matthias
%S Proceedings of BigScience Episode #5 – Workshop on Challenges & Perspectives in Creating Large Language Models
%D 2022
%8 May
%I Association for Computational Linguistics
%C virtual+Dublin
%F fries-etal-2022-dataset
%X Large-scale language modeling and natural language prompting have demonstrated exciting capabilities for few and zero shot learning in NLP. However, translating these successes to specialized domains such as biomedicine remains challenging, due in part to biomedical NLP’s significant dataset debt – the technical costs associated with data that are not consistently documented or easily incorporated into popular machine learning frameworks at scale. To assess this debt, we crowdsourced curation of datasheets for 167 biomedical datasets. We find that only 13% of datasets are available via programmatic access and 30% lack any documentation on licensing and permitted reuse. Our dataset catalog is available at: https://tinyurl.com/bigbio22.
%R 10.18653/v1/2022.bigscience-1.10
%U https://aclanthology.org/2022.bigscience-1.10
%U https://doi.org/10.18653/v1/2022.bigscience-1.10
%P 137-145
Markdown (Informal)
[Dataset Debt in Biomedical Language Modeling](https://aclanthology.org/2022.bigscience-1.10) (Fries et al., BigScience 2022)
ACL
- Jason Fries, Natasha Seelam, Gabriel Altay, Leon Weber, Myungsun Kang, Debajyoti Datta, Ruisi Su, Samuele Garda, Bo Wang, Simon Ott, Matthias Samwald, and Wojciech Kusa. 2022. Dataset Debt in Biomedical Language Modeling. In Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models, pages 137–145, virtual+Dublin. Association for Computational Linguistics.