AdaptOr: Objective-Centric Adaptation Framework for Language Models

Warning

This publication doesn't include Faculty of Economics and Administration. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

ŠTEFÁNIK Michal NOVOTNÝ Vít GROVEROVÁ Nikola SOJKA Petr

Year of publication 2022
Type Article in Proceedings
Conference Proceedings of the 60th Conference of Association of Computational Linguistics, ACL 2022
MU Faculty or unit

Faculty of Informatics

Citation
Web
Doi http://dx.doi.org/10.18653/v1/2022.acl-demo.26
Keywords Adaptor library; domain adaptation; similarity search; vector space; embeddings
Description Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces the Adaptor library that transposes the traditional model-centric approach composed of pre-training + fine-tuning steps to the objective-centric approach, composing the training process by applications of selected objectives. We survey research directions that can benefit from enhanced objective-centric experimentation in multitask training, custom objectives development, dynamic training curricula, or domain adaptation. Adaptor aims to ease the reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of Adaptor in selected unsupervised domain adaptation scenarios.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.