Data Governance in the Age of Large-Scale Data-Driven Language Technology

BibTex citation

@inproceedings{data_gov_bigscience,
    author = {Jernite, Yacine and Nguyen, Huu and Biderman, Stella and Rogers, Anna and Masoud, Maraim and Danchev, Valentin and Tan, Samson and Luccioni, Alexandra Sasha and Subramani, Nishant and Johnson, Isaac and Dupont, Gerard and Dodge, Jesse and Lo, Kyle and Talat, Zeerak and Radev, Dragomir and Gokaslan, Aaron and Nikpoor, Somaieh and Henderson, Peter and Bommasani, Rishi and Mitchell, Margaret},
    title = {Data Governance in the Age of Large-Scale Data-Driven Language Technology},
    year = {2022},
    isbn = {9781450393522},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3531146.3534637},
    doi = {10.1145/3531146.3534637},
    abstract = {The recent emergence and adoption of Machine Learning technology, and specifically of Large Language Models, has drawn attention to the need for systematic and transparent management of language data. This work proposes an approach to global language data governance that attempts to organize data management amongst stakeholders, values, and rights. Our proposal is informed by prior work on distributed governance that accounts for human values and grounded by an international research collaboration that brings together researchers and practitioners from 60 countries. The framework we present is a multi-party international governance structure focused on language data, and incorporating technical and organizational tools needed to support its work.},
    booktitle = {2022 ACM Conference on Fairness, Accountability, and Transparency},
    pages = {2206–2222},
    numpages = {17},
    keywords = {datasets, data rights, technology governance, language data},
    location = {Seoul, Republic of Korea},
    series = {FAccT '22}
}