Quantifying the Contextualization of Word Representations with Semantic Class Probing [article]

Mengjie Zhao, Philipp Dufter, Yadollah Yaghoobzadeh, Hinrich Schütze
2020 arXiv   pre-print
Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of contextualization, i.e., how well words are interpreted in context, by studying the extent to which semantic classes of a word can be inferred from its contextualized embeddings. Quantifying contextualization helps in understanding and utilizing pretrained
more » ... nguage models. We show that top layer representations achieve high accuracy inferring semantic classes; that the strongest contextualization effects occur in the lower layers; that local context is mostly sufficient for semantic class inference; and that top layer representations are more task-specific after finetuning while lower layer representations are more transferable. Finetuning uncovers task related features, but pretrained knowledge is still largely preserved.
arXiv:2004.12198v2 fatcat:crnslqh4jjb5bhizczlpdmtgay