Are Pre-trained Language Models Aware Of Phrases? Simple But Strong Baselines For Grammar Induction
Taeuk Kim, Jihun Choi, Daniel Edmiston, Sang-Goo Lee . Arxiv 2020 – 56 citations
With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings. In line with such interest, we propose a novel method that assists us in investigating the extent to which pre-trained LMs capture the syntactic notion of constituency. Our method provides an effective way of extracting constituency trees from the pre-trained LMs without training. In addition, we report intriguing findings in the induced trees, including the fact that pre-trained LMs outperform other approaches in correctly demarcating adverb phrases in sentences.