@inproceedings{mosbach-etal-2020-interplay-fine,
title = {On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers},
author = {Marius Mosbach and Anna Khokhlova and Michael Hedderich and Dietrich Klakow},
url = {https://www.aclweb.org/anthology/2020.findings-emnlp.227},
doi = {https://doi.org/10.18653/v1/2020.findings-emnlp.227},
year = {2020},
date = {2020},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020},
pages = {2502-2516},
publisher = {Association for Computational Linguistics},
abstract = {Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is, however, understood about how fine-tuning affects the representations of pre-trained models and thereby the linguistic knowledge they encode. This paper contributes towards closing this gap. We study three different pre-trained models: BERT, RoBERTa, and ALBERT, and investigate through sentence-level probing how fine-tuning affects their representations. We find that for some probing tasks fine-tuning leads to substantial changes in accuracy, possibly suggesting that fine-tuning introduces or even removes linguistic knowledge from a pre-trained model. These changes, however, vary greatly across different models, fine-tuning and probing tasks. Our analysis reveals that while fine-tuning indeed changes the representations of a pre-trained model and these changes are typically larger for higher layers, only in very few cases, fine-tuning has a positive effect on probing accuracy that is larger than just using the pre-trained model with a strong pooling method. Based on our findings, we argue that both positive and negative effects of fine-tuning on probing require a careful interpretation.},
pubstate = {published},
type = {inproceedings}
}