AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models. (arXiv:2206.11719v1 [cs.CL])

Web: http://arxiv.org/abs/2206.11719

The objective of pre-trained language models is to learn contextual
representations of textual data. Pre-trained language models have become
mainstream in natural language processing and code modeling. Using probes, a
technique to study the linguistic properties of hidden vector spaces, previous
works have shown that these pre-trained language models encode simple
linguistic properties in their hidden representations. However, none of the
previous work assessed whether these models encode the whole grammatical
structure of a programming language. In this paper, we …

arxiv language language models models probe syntax trees