Have Attention Heads in BERT Learned Constituency Grammar?
원문 초록
With the success of pre-trained language models in recent years, more and more researchers focus on opening the "black box" of these models. Following this interest, we carry out a qualitative and quantitative analysis of constituency grammar in attention heads of BERT and RoBERTa. We employ the syntactic distance method to extract implicit constituency grammar from the attention weights of each head. Our results show that there exist heads that can induce some grammar types much better than baselines, suggesting that some heads act as a proxy for constituency grammar. We also analyze how attention heads' constituency grammar inducing (CGI) ability changes after fine-tuning with two kinds of tasks, including sentence meaning similarity (SMS) tasks and natural language inference (NLI) tasks. Our results suggest that SMS tasks decrease the average CGI ability of upper layers, while NLI tasks increase it. Lastly, we investigate the connections between CGI ability and natural language understanding ability on QQP and MNLI tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A MISMATCHED Benchmark for Scientific Natural Language Inference
Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning
Parameter-Efficient Transformer Embeddings
skLEP: A Slovak General Language Understanding Benchmark
Semantic similarity estimation for domain specific data using BERT and other techniques
Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.