On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Statistical Analysis of Sentence Structures through ASCII, Lexical Alignment and PCA
A Comparative Analysis of Static Word Embeddings for Hungarian
FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)
myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging
A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950
Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging
토론
이 논문과 연결된 포럼 글이 아직 없습니다.