Adaptor: Objective-Centric Adaptation Framework for Language Models
This is an incremental contribution aimed at researchers in NLP to enhance reproducibility and experimentation in training processes.
The paper introduces Adaptor, a library that shifts from model-centric to objective-centric training for language models, and demonstrates its practical use in unsupervised domain adaptation scenarios.
Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces Adaptor library that transposes the traditional model-centric approach composed of pre-training + fine-tuning steps to 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 reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of Adaptor in selected unsupervised domain adaptation scenarios.