On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers
Marius Mosbach, Anna Khokhlova, Michael A. Hedderich, Dietrich Klakow · 2020
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 finetuning 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 finetuning 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 finetuning on probing require a careful interpretation.