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
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.- Anthology ID:
- 2020.blackboxnlp-1.7
- Volume:
- Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Afra Alishahi, Yonatan Belinkov, Grzegorz Chrupała, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad
- Venue:
- BlackboxNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 68–82
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2020.blackboxnlp-1.7/
- DOI:
- 10.18653/v1/2020.blackboxnlp-1.7
- Cite (ACL):
- Marius Mosbach, Anna Khokhlova, Michael A. Hedderich, and Dietrich Klakow. 2020. On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 68–82, Online. Association for Computational Linguistics.
- Cite (Informal):
- On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers (Mosbach et al., BlackboxNLP 2020)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2020.blackboxnlp-1.7.pdf