Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP

التفاصيل البيبلوغرافية
العنوان: Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
المؤلفون: Belz, Anya, Thomson, Craig, Reiter, Ehud, Abercrombie, Gavin, Alonso-Moral, Jose M., Arvan, Mohammad, Cheung, Jackie, Cieliebak, Mark, Clark, Elizabeth, Deemter, Kees van, Dinkar, Tanvi, Dušek, Ondřej, Eger, Steffen, Fang, Qixiang, Gatt, Albert, Gkatzia, Dimitra, González-Corbelle, Javier, Hovy, Dirk, Hürlimann, Manuela, Ito, Takumi, Kelleher, John D., Klubicka, Filip, Lai, Huiyuan, Lee, Chris van der, Miltenburg, Emiel van, Li, Yiru, Mahamood, Saad, Mieskes, Margot, Nissim, Malvina, Parde, Natalie, Plátek, Ondřej, Rieser, Verena, Romero, Pablo Mosteiro, Tetreault, Joel, Toral, Antonio, Wan, Xiaojun, Wanner, Leo, Watson, Lewis, Yang, Diyi
المساهمون: Sub Natural Language Processing, Leerstoel Oberski, Methodology and statistics for the behavioural and social sciences, Dep Informatica, Natural Language Processing
سنة النشر: 2023
الوصف: We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible. We present our results and findings, which include that just 13% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction, and that all but one of the experiments we selected for reproduction was discovered to have flaws that made the meaningfulness of conducting a reproduction questionable. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach. Our overall (negative) finding that the great majority of human evaluations in NLP is not repeatable and/or not reproducible and/or too flawed to justify reproduction, paints a dire picture, but presents an opportunity for a rethink about how to design and report human evaluations in NLP.
نوع الوثيقة: book part
وصف الملف: application/pdf
اللغة: English
العلاقة: https://dspace.library.uu.nl/handle/1874/429997Test
الإتاحة: https://dspace.library.uu.nl/handle/1874/429997Test
حقوق: info:eu-repo/semantics/OpenAccess
رقم الانضمام: edsbas.7EF665ED
قاعدة البيانات: BASE