Original Pdf: pdf
Code: [![github](/images/github_icon.svg) galsang/trees_from_transformers](https://github.com/galsang/trees_from_transformers)
Data: [MultiNLI](https://paperswithcode.com/dataset/multinli), [Penn Treebank](https://paperswithcode.com/dataset/penn-treebank)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2002.00737/code)
Abstract: 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.