A Study on How Attention Scores in the BERT Model are Aware of Lexical Categories in Syntactic and Semantic Tasks on the GLUE Benchmark

arXiv:2403.16447v1 Announce Type: new
Abstract: This study examines whether the attention scores between tokens in the BERT model significantly vary based on lexical categories during the fine-tuning process for downstream tasks. Drawing inspiration from the notion that in human language processing, syntactic and semantic information is parsed differently, we categorize tokens in sentences according to their lexical categories and focus on changes in attention scores among these categories. Our hypothesis posits that in downstream tasks that prioritize semantic information, attention …

abstract arxiv attention benchmark bert cs.cl fine-tuning glue inspiration notion process semantic study tasks tokens type