The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to more established disciplines, a lack of common experimental standards remains an open challenge to the field at large. Starting from fundamental scientific principles, we distill ongoing discussions on experimental standards in NLP into a single, widely-applicable methodology. Following these best practices is crucial to strengthen experimental evidence, improve reproducibility and support scientific progress. These standards are further collected in a public repository to help them transparently adapt to future needs.
@article{arxiv.2204.06251,
title = {Experimental Standards for Deep Learning in Natural Language Processing Research},
author = {Dennis Ulmer and Elisa Bassignana and Max Müller-Eberstein and Daniel Varab and Mike Zhang and Rob van der Goot and Christian Hardmeier and Barbara Plank},
journal= {arXiv preprint arXiv:2204.06251},
year = {2022}
}