AkihikoWatanabe / paper_notes

たまに追加される論文メモ
https://AkihikoWatanabe.github.io/paper_notes
17 stars 0 forks source link

What Does BERT Learn about the Structure of Language?, Jawahar+, ACL'19 #1446

Open AkihikoWatanabe opened 2 weeks ago

AkihikoWatanabe commented 2 weeks ago

https://aclanthology.org/P19-1356/

AkihikoWatanabe commented 2 weeks ago

BERT is a recent language representation model that has surprisingly performed well in diverse language understanding benchmarks. This result indicates the possibility that BERT networks capture structural information about language. In this work, we provide novel support for this claim by performing a series of experiments to unpack the elements of English language structure learned by BERT. Our findings are fourfold. BERT’s phrasal representation captures the phrase-level information in the lower layers. The intermediate layers of BERT compose a rich hierarchy of linguistic information, starting with surface features at the bottom, syntactic features in the middle followed by semantic features at the top. BERT requires deeper layers while tracking subject-verb agreement to handle long-term dependency problem. Finally, the compositional scheme underlying BERT mimics classical, tree-like structures.

Translation (by gpt-4o-mini)

AkihikoWatanabe commented 2 weeks ago

1370 中で引用されている。Transformerの各ブロックが、何を学習しているかを分析。