期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：2243-2258
DOI：10.18653/v1/2021.eacl-main.191
语种：English
出版社：ACL Anthology
摘要：The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations. Among other information, it has been shown that entire syntax trees are implicitly embedded in the geometry of such models. As these models are often fine-tuned, it becomes increasingly important to understand how the encoded knowledge evolves along the fine-tuning. In this paper, we analyze the evolution of the embedded syntax trees along the fine-tuning process of BERT for six different tasks, covering all levels of the linguistic structure. Experimental results show that the encoded syntactic information is forgotten (PoS tagging), reinforced (dependency and constituency parsing) or preserved (semantics-related tasks) in different ways along the fine-tuning process depending on the task.
