Skip to content
conftrace_

pretraining data size

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

pretraining data (1) syntax generalization (1) syntactic structural probe (1) downstream application (1) transformer model (1) syntactic probe (1) syntactic knowledge (1) syntactic generalization (1) part-of-speech tagging (1)

Papers

How much pretraining data do language models need to learn syntax? EMNLP 2021