Papers
arxiv:2203.10415

How does the pre-training objective affect what large language models learn about linguistic properties?

Published on Mar 20, 2022
Authors:

Abstract

Pre-training BERT with linguistically motivated objectives like masked language modeling does not significantly improve its linguistic knowledge compared to non-linguistically motivated objectives.

AI-generated summary

Several pre-training objectives, such as masked language modeling (MLM), have been proposed to pre-train language models (e.g. BERT) with the aim of learning better language representations. However, to the best of our knowledge, no previous work so far has investigated how different pre-training objectives affect what BERT learns about linguistics properties. We hypothesize that linguistically motivated objectives such as MLM should help BERT to acquire better linguistic knowledge compared to other non-linguistically motivated objectives that are not intuitive or hard for humans to guess the association between the input and the label to be predicted. To this end, we pre-train BERT with two linguistically motivated objectives and three non-linguistically motivated ones. We then probe for linguistic characteristics encoded in the representation of the resulting models. We find strong evidence that there are only small differences in probing performance between the representations learned by the two different types of objectives. These surprising results question the dominant narrative of linguistically informed pre-training.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2203.10415 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2203.10415 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2203.10415 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.