Слои
otherentity
ID: layers
Related Papers
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations
AbstractPretrained language models (PLMs) learn stereotypes held by humans and reflected in text from their training corpora, including gender bias. When PLMs are used for downstream tasks such as picking …...
Discourse Probing of Pretrained Language Models
AbstractExisting work on probing of pretrained language models (LMs) has predominantly focused on sentence-level syntactic tasks. In this paper, we introduce document-level discourse probing to evaluate the ability of pretrained …...