Linguistic Profiling of a Neural Language Model

10/05/2020 ∙ by Alessio Miaschi, et al. ∙ 10

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set of probing tasks, each of which corresponds to a distinct sentence-level feature extracted from different levels of linguistic annotation. We show that BERT is able to encode a wide range of linguistic characteristics, but it tends to lose this information when trained on specific downstream tasks. We also find that BERT's capacity to encode different kind of linguistic properties has a positive influence on its predictions: the more it stores readable linguistic information, the higher will be its capacity of predicting the correct label.



There are no comments yet.


page 5

page 7

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.